Merge branch 'v5.16' into fix/v5.16-version-alignment

- Update SDK version: 5.16.0 → 5.16.1
- Update UI version: v5.12.2 → v5.16.1
- Update API version: 1.17.0 → 1.17.1
- Update documentation versions to 5.16.0

Ensures all component versions follow the correct versioning scheme:
- SDK/UI: 5.16.x
- API: 1.17.x (Prowler minor + 1)

.env

@@ -15,6 +15,13 @@ AUTH_SECRET="N/c6mnaS5+SWq81+819OrzQZlmx1Vxtp/orjttJSmw8="
 # Google Tag Manager ID
 NEXT_PUBLIC_GOOGLE_TAG_MANAGER_ID=""
 
+#### MCP Server ####
+PROWLER_MCP_VERSION=stable
+# For UI and MCP running on docker:
+PROWLER_MCP_SERVER_URL=http://mcp-server:8000/mcp
+# For UI running on host, MCP in docker:
+# PROWLER_MCP_SERVER_URL=http://localhost:8000/mcp
+
 #### Code Review Configuration ####
 # Enable Claude Code standards validation on pre-push hook
 # Set to 'true' to validate changes against AGENTS.md standards via Claude Code
@@ -112,7 +119,7 @@ NEXT_PUBLIC_SENTRY_ENVIRONMENT=${SENTRY_ENVIRONMENT}
 
 
 #### Prowler release version ####
-NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.12.2
+NEXT_PUBLIC_PROWLER_RELEASE_VERSION=v5.16.1
 
 # Social login credentials
 SOCIAL_GOOGLE_OAUTH_CALLBACK_URL="${AUTH_URL}/api/auth/callback/google"

.github/workflows/api-container-checks.yml

@@ -20,6 +20,7 @@ env:
 
 jobs:
   api-dockerfile-lint:
+    if: github.repository == 'prowler-cloud/prowler'
     runs-on: ubuntu-latest
     timeout-minutes: 15
     permissions:
@@ -43,6 +44,7 @@ jobs:
           ignore: DL3013
 
   api-container-build-and-scan:
+    if: github.repository == 'prowler-cloud/prowler'
     runs-on: ${{ matrix.runner }}
     strategy:
       matrix:
@@ -90,7 +92,7 @@ jobs:
           cache-to: type=gha,mode=max,scope=${{ matrix.arch }}
 
       - name: Scan container with Trivy for ${{ matrix.arch }}
-        if: github.repository == 'prowler-cloud/prowler' && steps.check-changes.outputs.any_changed == 'true'
+        if: steps.check-changes.outputs.any_changed == 'true'
         uses: ./.github/actions/trivy-scan
         with:
           image-name: ${{ env.IMAGE_NAME }}

.github/workflows/mcp-container-checks.yml

@@ -20,6 +20,7 @@ env:
 
 jobs:
   mcp-dockerfile-lint:
+    if: github.repository == 'prowler-cloud/prowler'
     runs-on: ubuntu-latest
     timeout-minutes: 15
     permissions:
@@ -42,6 +43,7 @@ jobs:
           dockerfile: mcp_server/Dockerfile
 
   mcp-container-build-and-scan:
+    if: github.repository == 'prowler-cloud/prowler'
     runs-on: ${{ matrix.runner }}
     strategy:
       matrix:
@@ -88,7 +90,7 @@ jobs:
           cache-to: type=gha,mode=max,scope=${{ matrix.arch }}
 
       - name: Scan MCP container with Trivy for ${{ matrix.arch }}
-        if: github.repository == 'prowler-cloud/prowler' && steps.check-changes.outputs.any_changed == 'true'
+        if: steps.check-changes.outputs.any_changed == 'true'
         uses: ./.github/actions/trivy-scan
         with:
           image-name: ${{ env.IMAGE_NAME }}

.github/workflows/sdk-container-checks.yml

@@ -104,7 +104,7 @@ jobs:
           cache-to: type=gha,mode=max,scope=${{ matrix.arch }}
 
       - name: Scan SDK container with Trivy for ${{ matrix.arch }}
-        if: github.repository == 'prowler-cloud/prowler' && steps.check-changes.outputs.any_changed == 'true'
+        if: steps.check-changes.outputs.any_changed == 'true'
         uses: ./.github/actions/trivy-scan
         with:
           image-name: ${{ env.IMAGE_NAME }}

.github/workflows/ui-container-checks.yml

@@ -20,6 +20,7 @@ env:
 
 jobs:
   ui-dockerfile-lint:
+    if: github.repository == 'prowler-cloud/prowler'
     runs-on: ubuntu-latest
     timeout-minutes: 10
     permissions:
@@ -43,6 +44,7 @@ jobs:
           ignore: DL3018
 
   ui-container-build-and-scan:
+    if: github.repository == 'prowler-cloud/prowler'
     runs-on: ${{ matrix.runner }}
     strategy:
       matrix:
@@ -92,7 +94,7 @@ jobs:
             NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=pk_test_51LwpXXXX
 
       - name: Scan UI container with Trivy for ${{ matrix.arch }}
-        if: github.repository == 'prowler-cloud/prowler' && steps.check-changes.outputs.any_changed == 'true'
+        if: steps.check-changes.outputs.any_changed == 'true'
         uses: ./.github/actions/trivy-scan
         with:
           image-name: ${{ env.IMAGE_NAME }}

Makefile

@@ -47,12 +47,12 @@ help:     ## Show this help.
 	@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n  make \033[36m<target>\033[0m\n"} /^[a-zA-Z_-]+:.*?##/ { printf "  \033[36m%-15s\033[0m %s\n", $$1, $$2 } /^##@/ { printf "\n\033[1m%s\033[0m\n", substr($$0, 5) } ' $(MAKEFILE_LIST)
 
 ##@ Build no cache
-build-no-cache-dev: 
-	docker compose -f docker-compose-dev.yml build --no-cache api-dev worker-dev worker-beat
+build-no-cache-dev:
+	docker compose -f docker-compose-dev.yml build --no-cache api-dev worker-dev worker-beat mcp-server
 
 ##@ Development Environment
-run-api-dev: ## Start development environment with API, PostgreSQL, Valkey, and workers 
-	docker compose -f docker-compose-dev.yml up api-dev postgres valkey worker-dev worker-beat
+run-api-dev: ## Start development environment with API, PostgreSQL, Valkey, MCP, and workers
+	docker compose -f docker-compose-dev.yml up api-dev postgres valkey worker-dev worker-beat mcp-server
 
 ##@ Development Environment
 build-and-run-api-dev: build-no-cache-dev run-api-dev

README.md

@@ -23,6 +23,7 @@
   <a href="https://hub.docker.com/r/toniblyx/prowler"><img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/toniblyx/prowler"></a>
   <a href="https://gallery.ecr.aws/prowler-cloud/prowler"><img width="120" height=19" alt="AWS ECR Gallery" src="https://user-images.githubusercontent.com/3985464/151531396-b6535a68-c907-44eb-95a1-a09508178616.png"></a>
   <a href="https://codecov.io/gh/prowler-cloud/prowler"><img src="https://codecov.io/gh/prowler-cloud/prowler/graph/badge.svg?token=OflBGsdpDl"/></a>
+  <a href="https://insights.linuxfoundation.org/project/prowler-cloud-prowler"><img src="https://insights.linuxfoundation.org/api/badge/health-score?project=prowler-cloud-prowler"/></a>
 </p>
 <p align="center">
     <a href="https://github.com/prowler-cloud/prowler/releases"><img alt="Version" src="https://img.shields.io/github/v/release/prowler-cloud/prowler"></a>
@@ -276,11 +277,12 @@ python prowler-cli.py -v
 # ✏️ High level architecture
 
 ## Prowler App
-**Prowler App** is composed of three key components:
+**Prowler App** is composed of four key components:
 
 - **Prowler UI**: A web-based interface, built with Next.js, providing a user-friendly experience for executing Prowler scans and visualizing results.
 - **Prowler API**: A backend service, developed with Django REST Framework, responsible for running Prowler scans and storing the generated results.
 - **Prowler SDK**: A Python SDK designed to extend the functionality of the Prowler CLI for advanced capabilities.
+- **Prowler MCP Server**: A Model Context Protocol server that provides AI tools for Lighthouse, the AI-powered security assistant. This is a critical dependency for Lighthouse functionality.
 
 ![Prowler App Architecture](docs/products/img/prowler-app-architecture.png)
 

api/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 All notable changes to the **Prowler API** are documented in this file.
 
+## [1.17.0] (Prowler v5.16.0)
+
+### Added
+- New endpoint to retrieve and overview of the categories based on finding severities [(#9529)](https://github.com/prowler-cloud/prowler/pull/9529)
+- Endpoints `GET /findings` and `GET /findings/latests` can now use the category filter [(#9529)](https://github.com/prowler-cloud/prowler/pull/9529)
+- Account id, alias and provider name to PDF reporting table [(#9574)](https://github.com/prowler-cloud/prowler/pull/9574)
+
+### Changed
+- Endpoint `GET /overviews/attack-surfaces` no longer returns the related check IDs [(#9529)](https://github.com/prowler-cloud/prowler/pull/9529)
+- OpenAI provider to only load chat-compatible models with tool calling support [(#9523)](https://github.com/prowler-cloud/prowler/pull/9523)
+- Increased execution delay for the first scheduled scan tasks to 5 seconds[(#9558)](https://github.com/prowler-cloud/prowler/pull/9558)
+
+### Fixed
+- Made `scan_id` a required filter in the compliance overview endpoint [(#9560)](https://github.com/prowler-cloud/prowler/pull/9560)
+- Reduced unnecessary UPDATE resources operations by only saving when tag mappings change, lowering write load during scans [(#9569)](https://github.com/prowler-cloud/prowler/pull/9569)
+
+---
+
 ## [1.16.1] (Prowler v5.15.1)
 
 ### Fixed

api/poetry.lock

@@ -2070,14 +2070,13 @@ tests = ["pytest", "pytest-cov", "pytest-xdist"]
 
 [[package]]
 name = "darabonba-core"
-version = "1.0.4"
+version = "1.0.5"
 description = "The darabonba module of alibabaCloud Python SDK."
 optional = false
 python-versions = ">=3.7"
 groups = ["main"]
 files = [
-    {file = "darabonba_core-1.0.4-py3-none-any.whl", hash = "sha256:4c3bc1d76d5af1087297b6afde8e960ea2f54f93e725e2df8453f0b4bb27dd24"},
-    {file = "darabonba_core-1.0.4.tar.gz", hash = "sha256:6ede4e9bfd458148bab19ab2331716ae9b5c226ba5f6d221de6f88ee65704137"},
+    {file = "darabonba_core-1.0.5-py3-none-any.whl", hash = "sha256:671ab8dbc4edc2a8f88013da71646839bb8914f1259efc069353243ef52ea27c"},
 ]
 
 [package.dependencies]
@@ -5409,7 +5408,7 @@ files = [
 
 [[package]]
 name = "prowler"
-version = "5.15.0"
+version = "5.16.0"
 description = "Prowler is an Open Source security tool to perform AWS, GCP and Azure security best practices assessments, audits, incident response, continuous monitoring, hardening and forensics readiness. It contains hundreds of controls covering CIS, NIST 800, NIST CSF, CISA, RBI, FedRAMP, PCI-DSS, GDPR, HIPAA, FFIEC, SOC2, GXP, AWS Well-Architected Framework Security Pillar, AWS Foundational Technical Review (FTR), ENS (Spanish National Security Scheme) and your custom security frameworks."
 optional = false
 python-versions = ">3.9.1,<3.13"
@@ -5494,8 +5493,8 @@ tzlocal = "5.3.1"
 [package.source]
 type = "git"
 url = "https://github.com/prowler-cloud/prowler.git"
-reference = "v5.15"
-resolved_reference = "e2f30e0987f5e0f46e90a6c547258bb850e36d78"
+reference = "v5.16"
+resolved_reference = "f0e59bcb13383d7bb1aa9804906ac99aed820a09"
 
 [[package]]
 name = "psutil"
@@ -7847,4 +7846,4 @@ files = [
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.11,<3.13"
-content-hash = "dd974908bc16c3730c76f18506e8a5cdd1b726965ab8fa05336b22ab1b5ab7be"
+content-hash = "c3f69105de7e604d4978c53877203d69c59d22276e8d7c751f4960764a5f926c"

api/pyproject.toml

@@ -24,7 +24,7 @@ dependencies = [
   "drf-spectacular-jsonapi==0.5.1",
   "gunicorn==23.0.0",
   "lxml==5.3.2",
-  "prowler @ git+https://github.com/prowler-cloud/prowler.git@v5.15",
+  "prowler @ git+https://github.com/prowler-cloud/prowler.git@v5.16",
   "psycopg2-binary==2.9.9",
   "pytest-celery[redis] (>=1.0.1,<2.0.0)",
   "sentry-sdk[django] (>=2.20.0,<3.0.0)",
@@ -44,7 +44,7 @@ name = "prowler-api"
 package-mode = false
 # Needed for the SDK compatibility
 requires-python = ">=3.11,<3.13"
-version = "1.16.1"
+version = "1.17.1"
 
 [project.scripts]
 celery = "src.backend.config.settings.celery"

api/src/backend/api/apps.py

@@ -40,7 +40,6 @@ class ApiConfig(AppConfig):
             self._ensure_crypto_keys()
 
         load_prowler_compliance()
-        self._initialize_attack_surface_mapping()
 
     def _ensure_crypto_keys(self):
         """
@@ -168,13 +167,3 @@ class ApiConfig(AppConfig):
                 f"Error generating JWT keys: {e}. Please set '{SIGNING_KEY_ENV}' and '{VERIFYING_KEY_ENV}' manually."
             )
             raise e
-
-    def _initialize_attack_surface_mapping(self):
-        from tasks.jobs.scan import (  # noqa: F401
-            _get_attack_surface_mapping_from_provider,
-        )
-
-        from api.models import Provider  # noqa: F401
-
-        for provider_type, _label in Provider.ProviderChoices.choices:
-            _get_attack_surface_mapping_from_provider(provider_type)

api/src/backend/api/filters.py

@@ -43,6 +43,7 @@ from api.models import (
     ResourceTag,
     Role,
     Scan,
+    ScanCategorySummary,
     ScanSummary,
     SeverityChoices,
     StateChoices,
@@ -157,6 +158,9 @@ class CommonFindingFilters(FilterSet):
         field_name="resources__type", lookup_expr="icontains"
     )
 
+    category = CharFilter(method="filter_category")
+    category__in = CharInFilter(field_name="categories", lookup_expr="overlap")
+
     # Temporarily disabled until we implement tag filtering in the UI
     # resource_tag_key = CharFilter(field_name="resources__tags__key")
     # resource_tag_key__in = CharInFilter(
@@ -188,6 +192,9 @@ class CommonFindingFilters(FilterSet):
     def filter_resource_type(self, queryset, name, value):
         return queryset.filter(resource_types__contains=[value])
 
+    def filter_category(self, queryset, name, value):
+        return queryset.filter(categories__contains=[value])
+
     def filter_resource_tag(self, queryset, name, value):
         overall_query = Q()
         for key_value_pair in value:
@@ -762,7 +769,7 @@ class RoleFilter(FilterSet):
 
 class ComplianceOverviewFilter(FilterSet):
     inserted_at = DateFilter(field_name="inserted_at", lookup_expr="date")
-    scan_id = UUIDFilter(field_name="scan_id")
+    scan_id = UUIDFilter(field_name="scan_id", required=True)
     region = CharFilter(field_name="region")
 
     class Meta:
@@ -1096,3 +1103,22 @@ class AttackSurfaceOverviewFilter(FilterSet):
     class Meta:
         model = AttackSurfaceOverview
         fields = {}
+
+
+class CategoryOverviewFilter(FilterSet):
+    provider_id = UUIDFilter(field_name="scan__provider__id", lookup_expr="exact")
+    provider_id__in = UUIDInFilter(field_name="scan__provider__id", lookup_expr="in")
+    provider_type = ChoiceFilter(
+        field_name="scan__provider__provider", choices=Provider.ProviderChoices.choices
+    )
+    provider_type__in = ChoiceInFilter(
+        field_name="scan__provider__provider",
+        choices=Provider.ProviderChoices.choices,
+        lookup_expr="in",
+    )
+    category = CharFilter(field_name="category", lookup_expr="exact")
+    category__in = CharInFilter(field_name="category", lookup_expr="in")
+
+    class Meta:
+        model = ScanCategorySummary
+        fields = {}

api/src/backend/api/migrations/0063_scan_category_summary.py

@@ -0,0 +1,111 @@
+import uuid
+
+import django.db.models.deletion
+from django.db import migrations, models
+
+import api.db_utils
+import api.rls
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0062_backfill_daily_severity_summaries"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="ScanCategorySummary",
+            fields=[
+                (
+                    "id",
+                    models.UUIDField(
+                        default=uuid.uuid4,
+                        editable=False,
+                        primary_key=True,
+                        serialize=False,
+                    ),
+                ),
+                (
+                    "tenant",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to="api.tenant",
+                    ),
+                ),
+                (
+                    "inserted_at",
+                    models.DateTimeField(auto_now_add=True),
+                ),
+                (
+                    "scan",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="category_summaries",
+                        related_query_name="category_summary",
+                        to="api.scan",
+                    ),
+                ),
+                (
+                    "category",
+                    models.CharField(max_length=100),
+                ),
+                (
+                    "severity",
+                    api.db_utils.SeverityEnumField(
+                        choices=[
+                            ("critical", "Critical"),
+                            ("high", "High"),
+                            ("medium", "Medium"),
+                            ("low", "Low"),
+                            ("informational", "Informational"),
+                        ],
+                    ),
+                ),
+                (
+                    "total_findings",
+                    models.IntegerField(
+                        default=0, help_text="Non-muted findings (PASS + FAIL)"
+                    ),
+                ),
+                (
+                    "failed_findings",
+                    models.IntegerField(
+                        default=0,
+                        help_text="Non-muted FAIL findings (subset of total_findings)",
+                    ),
+                ),
+                (
+                    "new_failed_findings",
+                    models.IntegerField(
+                        default=0,
+                        help_text="Non-muted FAIL with delta='new' (subset of failed_findings)",
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "scan_category_summaries",
+                "abstract": False,
+            },
+        ),
+        migrations.AddIndex(
+            model_name="scancategorysummary",
+            index=models.Index(
+                fields=["tenant_id", "scan"], name="scs_tenant_scan_idx"
+            ),
+        ),
+        migrations.AddConstraint(
+            model_name="scancategorysummary",
+            constraint=models.UniqueConstraint(
+                fields=("tenant_id", "scan_id", "category", "severity"),
+                name="unique_category_severity_per_scan",
+            ),
+        ),
+        migrations.AddConstraint(
+            model_name="scancategorysummary",
+            constraint=api.rls.RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_scancategorysummary",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ),
+    ]

api/src/backend/api/migrations/0064_finding_categories.py

@@ -0,0 +1,22 @@
+import django.contrib.postgres.fields
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0063_scan_category_summary"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="finding",
+            name="categories",
+            field=django.contrib.postgres.fields.ArrayField(
+                base_field=models.CharField(max_length=100),
+                blank=True,
+                null=True,
+                size=None,
+                help_text="Categories from check metadata for efficient filtering",
+            ),
+        ),
+    ]

api/src/backend/api/models.py

@@ -716,14 +716,19 @@ class Resource(RowLevelSecurityProtectedModel):
             self.clear_tags()
             return
 
-        # Add new relationships with the tenant_id field
+        # Add new relationships with the tenant_id field; avoid touching the
+        # Resource row unless a mapping is actually created to prevent noisy
+        # updates during scans.
+        mapping_created = False
         for tag in tags:
-            ResourceTagMapping.objects.update_or_create(
+            _, created = ResourceTagMapping.objects.update_or_create(
                 tag=tag, resource=self, tenant_id=self.tenant_id
             )
+            mapping_created = mapping_created or created
 
-        # Save the instance
-        self.save()
+        if mapping_created:
+            # Only bump updated_at when the tag set truly changed
+            self.save(update_fields=["updated_at"])
 
     class Meta(RowLevelSecurityProtectedModel.Meta):
         db_table = "resources"
@@ -868,6 +873,14 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
         null=True,
     )
 
+    # Check metadata denormalization
+    categories = ArrayField(
+        models.CharField(max_length=100),
+        blank=True,
+        null=True,
+        help_text="Categories from check metadata for efficient filtering",
+    )
+
     # Relationships
     scan = models.ForeignKey(to=Scan, related_name="findings", on_delete=models.CASCADE)
 
@@ -1951,6 +1964,64 @@ class ResourceScanSummary(RowLevelSecurityProtectedModel):
         ]
 
 
+class ScanCategorySummary(RowLevelSecurityProtectedModel):
+    """
+    Pre-aggregated category metrics per scan by severity.
+
+    Stores one row per (category, severity) combination per scan for efficient
+    overview queries. Categories come from check_metadata.categories.
+
+    Count relationships (each is a subset of the previous):
+        - total_findings >= failed_findings >= new_failed_findings
+    """
+
+    id = models.UUIDField(primary_key=True, default=uuid4, editable=False)
+    inserted_at = models.DateTimeField(auto_now_add=True, editable=False)
+
+    scan = models.ForeignKey(
+        Scan,
+        on_delete=models.CASCADE,
+        related_name="category_summaries",
+        related_query_name="category_summary",
+    )
+
+    category = models.CharField(max_length=100)
+    severity = SeverityEnumField(choices=SeverityChoices)
+
+    total_findings = models.IntegerField(
+        default=0, help_text="Non-muted findings (PASS + FAIL)"
+    )
+    failed_findings = models.IntegerField(
+        default=0, help_text="Non-muted FAIL findings (subset of total_findings)"
+    )
+    new_failed_findings = models.IntegerField(
+        default=0,
+        help_text="Non-muted FAIL with delta='new' (subset of failed_findings)",
+    )
+
+    class Meta(RowLevelSecurityProtectedModel.Meta):
+        db_table = "scan_category_summaries"
+
+        indexes = [
+            models.Index(fields=["tenant_id", "scan"], name="scs_tenant_scan_idx"),
+        ]
+
+        constraints = [
+            models.UniqueConstraint(
+                fields=("tenant_id", "scan_id", "category", "severity"),
+                name="unique_category_severity_per_scan",
+            ),
+            RowLevelSecurityConstraint(
+                field="tenant_id",
+                name="rls_on_%(class)s",
+                statements=["SELECT", "INSERT", "UPDATE", "DELETE"],
+            ),
+        ]
+
+    class JSONAPIMeta:
+        resource_name = "scan-category-summaries"
+
+
 class LighthouseConfiguration(RowLevelSecurityProtectedModel):
     """
     Stores configuration and API keys for LLM services.

api/src/backend/api/specs/v1.yaml

@@ -1,7 +1,7 @@
 openapi: 3.0.3
 info:
   title: Prowler API
-  version: 1.16.1
+  version: 1.17.1
   description: |-
     Prowler API specification.
 
@@ -711,6 +711,7 @@ paths:
             - severity
             - check_id
             - check_metadata
+            - categories
             - raw_result
             - inserted_at
             - updated_at
@@ -723,6 +724,19 @@ paths:
         description: endpoint return only specific fields in the response on a per-type
           basis by including a fields[TYPE] query parameter.
         explode: false
+      - in: query
+        name: filter[category]
+        schema:
+          type: string
+      - in: query
+        name: filter[category__in]
+        schema:
+          type: array
+          items:
+            type: string
+        description: Multiple values may be separated by commas.
+        explode: false
+        style: form
       - in: query
         name: filter[check_id]
         schema:
@@ -1205,6 +1219,7 @@ paths:
             - severity
             - check_id
             - check_metadata
+            - categories
             - raw_result
             - inserted_at
             - updated_at
@@ -1265,6 +1280,19 @@ paths:
         description: endpoint return only specific fields in the response on a per-type
           basis by including a fields[TYPE] query parameter.
         explode: false
+      - in: query
+        name: filter[category]
+        schema:
+          type: string
+      - in: query
+        name: filter[category__in]
+        schema:
+          type: array
+          items:
+            type: string
+        description: Multiple values may be separated by commas.
+        explode: false
+        style: form
       - in: query
         name: filter[check_id]
         schema:
@@ -1722,6 +1750,7 @@ paths:
             - severity
             - check_id
             - check_metadata
+            - categories
             - raw_result
             - inserted_at
             - updated_at
@@ -1734,6 +1763,19 @@ paths:
         description: endpoint return only specific fields in the response on a per-type
           basis by including a fields[TYPE] query parameter.
         explode: false
+      - in: query
+        name: filter[category]
+        schema:
+          type: string
+      - in: query
+        name: filter[category__in]
+        schema:
+          type: array
+          items:
+            type: string
+        description: Multiple values may be separated by commas.
+        explode: false
+        style: form
       - in: query
         name: filter[check_id]
         schema:
@@ -2151,9 +2193,23 @@ paths:
             - services
             - regions
             - resource_types
+            - categories
         description: endpoint return only specific fields in the response on a per-type
           basis by including a fields[TYPE] query parameter.
         explode: false
+      - in: query
+        name: filter[category]
+        schema:
+          type: string
+      - in: query
+        name: filter[category__in]
+        schema:
+          type: array
+          items:
+            type: string
+        description: Multiple values may be separated by commas.
+        explode: false
+        style: form
       - in: query
         name: filter[check_id]
         schema:
@@ -2609,9 +2665,23 @@ paths:
             - services
             - regions
             - resource_types
+            - categories
         description: endpoint return only specific fields in the response on a per-type
           basis by including a fields[TYPE] query parameter.
         explode: false
+      - in: query
+        name: filter[category]
+        schema:
+          type: string
+      - in: query
+        name: filter[category__in]
+        schema:
+          type: array
+          items:
+            type: string
+        description: Multiple values may be separated by commas.
+        explode: false
+        style: form
       - in: query
         name: filter[check_id]
         schema:
@@ -4499,7 +4569,7 @@ paths:
           description: No response body
   /api/v1/overviews/attack-surfaces:
     get:
-      operationId: overviews_attack_surfaces_retrieve
+      operationId: overviews_attack_surfaces_list
       description: Retrieve aggregated attack surface metrics from latest completed
         scans per provider.
       summary: Get attack surface overview
@@ -4515,31 +4585,116 @@ paths:
             - total_findings
             - failed_findings
             - muted_failed_findings
-            - check_ids
         description: endpoint return only specific fields in the response on a per-type
           basis by including a fields[TYPE] query parameter.
         explode: false
-      - in: query
-        name: filter[provider_id.in]
-        schema:
-          type: string
-        description: Filter by multiple provider IDs (comma-separated UUIDs)
       - in: query
         name: filter[provider_id]
         schema:
           type: string
           format: uuid
-        description: Filter by specific provider ID
       - in: query
-        name: filter[provider_type.in]
+        name: filter[provider_id__in]
         schema:
-          type: string
-        description: Filter by multiple provider types (comma-separated)
+          type: array
+          items:
+            type: string
+            format: uuid
+        description: Multiple values may be separated by commas.
+        explode: false
+        style: form
       - in: query
         name: filter[provider_type]
         schema:
           type: string
-        description: Filter by provider type (aws, azure, gcp, etc.)
+          x-spec-enum-id: eca8c51e6bd28935
+          enum:
+          - aws
+          - azure
+          - gcp
+          - github
+          - iac
+          - kubernetes
+          - m365
+          - mongodbatlas
+          - oraclecloud
+        description: |-
+          * `aws` - AWS
+          * `azure` - Azure
+          * `gcp` - GCP
+          * `kubernetes` - Kubernetes
+          * `m365` - M365
+          * `github` - GitHub
+          * `mongodbatlas` - MongoDB Atlas
+          * `iac` - IaC
+          * `oraclecloud` - Oracle Cloud Infrastructure
+      - in: query
+        name: filter[provider_type__in]
+        schema:
+          type: array
+          items:
+            type: string
+            x-spec-enum-id: eca8c51e6bd28935
+            enum:
+            - aws
+            - azure
+            - gcp
+            - github
+            - iac
+            - kubernetes
+            - m365
+            - mongodbatlas
+            - oraclecloud
+        description: |-
+          Multiple values may be separated by commas.
+
+          * `aws` - AWS
+          * `azure` - Azure
+          * `gcp` - GCP
+          * `kubernetes` - Kubernetes
+          * `m365` - M365
+          * `github` - GitHub
+          * `mongodbatlas` - MongoDB Atlas
+          * `iac` - IaC
+          * `oraclecloud` - Oracle Cloud Infrastructure
+        explode: false
+        style: form
+      - name: filter[search]
+        required: false
+        in: query
+        description: A search term.
+        schema:
+          type: string
+      - name: page[number]
+        required: false
+        in: query
+        description: A page number within the paginated result set.
+        schema:
+          type: integer
+      - name: page[size]
+        required: false
+        in: query
+        description: Number of results to return per page.
+        schema:
+          type: integer
+      - name: sort
+        required: false
+        in: query
+        description: '[list of fields to sort by](https://jsonapi.org/format/#fetching-sorting)'
+        schema:
+          type: array
+          items:
+            type: string
+            enum:
+            - id
+            - -id
+            - total_findings
+            - -total_findings
+            - failed_findings
+            - -failed_findings
+            - muted_failed_findings
+            - -muted_failed_findings
+        explode: false
       tags:
       - Overview
       security:
@@ -4549,7 +4704,164 @@ paths:
           content:
             application/vnd.api+json:
               schema:
-                $ref: '#/components/schemas/AttackSurfaceOverviewResponse'
+                $ref: '#/components/schemas/PaginatedAttackSurfaceOverviewList'
+          description: ''
+  /api/v1/overviews/categories:
+    get:
+      operationId: overviews_categories_list
+      description: 'Retrieve aggregated category metrics from latest completed scans
+        per provider. Returns one row per category with total, failed, and new failed
+        findings counts, plus a severity breakdown showing failed findings per severity
+        level. '
+      summary: Get category overview
+      parameters:
+      - in: query
+        name: fields[category-overviews]
+        schema:
+          type: array
+          items:
+            type: string
+            enum:
+            - id
+            - total_findings
+            - failed_findings
+            - new_failed_findings
+            - severity
+        description: endpoint return only specific fields in the response on a per-type
+          basis by including a fields[TYPE] query parameter.
+        explode: false
+      - in: query
+        name: filter[category]
+        schema:
+          type: string
+      - in: query
+        name: filter[category__in]
+        schema:
+          type: array
+          items:
+            type: string
+        description: Multiple values may be separated by commas.
+        explode: false
+        style: form
+      - in: query
+        name: filter[provider_id]
+        schema:
+          type: string
+          format: uuid
+      - in: query
+        name: filter[provider_id__in]
+        schema:
+          type: array
+          items:
+            type: string
+            format: uuid
+        description: Multiple values may be separated by commas.
+        explode: false
+        style: form
+      - in: query
+        name: filter[provider_type]
+        schema:
+          type: string
+          x-spec-enum-id: eca8c51e6bd28935
+          enum:
+          - aws
+          - azure
+          - gcp
+          - github
+          - iac
+          - kubernetes
+          - m365
+          - mongodbatlas
+          - oraclecloud
+        description: |-
+          * `aws` - AWS
+          * `azure` - Azure
+          * `gcp` - GCP
+          * `kubernetes` - Kubernetes
+          * `m365` - M365
+          * `github` - GitHub
+          * `mongodbatlas` - MongoDB Atlas
+          * `iac` - IaC
+          * `oraclecloud` - Oracle Cloud Infrastructure
+      - in: query
+        name: filter[provider_type__in]
+        schema:
+          type: array
+          items:
+            type: string
+            x-spec-enum-id: eca8c51e6bd28935
+            enum:
+            - aws
+            - azure
+            - gcp
+            - github
+            - iac
+            - kubernetes
+            - m365
+            - mongodbatlas
+            - oraclecloud
+        description: |-
+          Multiple values may be separated by commas.
+
+          * `aws` - AWS
+          * `azure` - Azure
+          * `gcp` - GCP
+          * `kubernetes` - Kubernetes
+          * `m365` - M365
+          * `github` - GitHub
+          * `mongodbatlas` - MongoDB Atlas
+          * `iac` - IaC
+          * `oraclecloud` - Oracle Cloud Infrastructure
+        explode: false
+        style: form
+      - name: filter[search]
+        required: false
+        in: query
+        description: A search term.
+        schema:
+          type: string
+      - name: page[number]
+        required: false
+        in: query
+        description: A page number within the paginated result set.
+        schema:
+          type: integer
+      - name: page[size]
+        required: false
+        in: query
+        description: Number of results to return per page.
+        schema:
+          type: integer
+      - name: sort
+        required: false
+        in: query
+        description: '[list of fields to sort by](https://jsonapi.org/format/#fetching-sorting)'
+        schema:
+          type: array
+          items:
+            type: string
+            enum:
+            - id
+            - -id
+            - total_findings
+            - -total_findings
+            - failed_findings
+            - -failed_findings
+            - new_failed_findings
+            - -new_failed_findings
+            - severity
+            - -severity
+        explode: false
+      tags:
+      - Overview
+      security:
+      - JWT or API Key: []
+      responses:
+        '200':
+          content:
+            application/vnd.api+json:
+              schema:
+                $ref: '#/components/schemas/PaginatedCategoryOverviewList'
           description: ''
   /api/v1/overviews/findings:
     get:
@@ -4951,7 +5263,7 @@ paths:
       summary: Get findings severity data over time
       parameters:
       - in: query
-        name: fields[findings-severity-timeseries]
+        name: fields[findings-severity-over-time]
         schema:
           type: array
           items:
@@ -4972,10 +5284,12 @@ paths:
         name: filter[date_from]
         schema:
           type: string
+          format: date
       - in: query
         name: filter[date_to]
         schema:
           type: string
+          format: date
       - in: query
         name: filter[provider_id]
         schema:
@@ -10846,23 +11160,46 @@ components:
               type: integer
             muted_failed_findings:
               type: integer
-            check_ids:
-              type: array
-              items:
-                type: string
-              readOnly: true
           required:
           - id
           - total_findings
           - failed_findings
           - muted_failed_findings
-    AttackSurfaceOverviewResponse:
+    CategoryOverview:
       type: object
-      properties:
-        data:
-          $ref: '#/components/schemas/AttackSurfaceOverview'
       required:
-      - data
+      - type
+      - id
+      additionalProperties: false
+      properties:
+        type:
+          type: string
+          description: The [type](https://jsonapi.org/format/#document-resource-object-identification)
+            member is used to describe resource objects that share common attributes
+            and relationships.
+          enum:
+          - category-overviews
+        id: {}
+        attributes:
+          type: object
+          properties:
+            id:
+              type: string
+            total_findings:
+              type: integer
+            failed_findings:
+              type: integer
+            new_failed_findings:
+              type: integer
+            severity:
+              description: 'Severity breakdown: {informational, low, medium, high,
+                critical}'
+          required:
+          - id
+          - total_findings
+          - failed_findings
+          - new_failed_findings
+          - severity
     ComplianceOverview:
       type: object
       required:
@@ -11079,6 +11416,13 @@ components:
               type: string
               maxLength: 100
             check_metadata: {}
+            categories:
+              type: array
+              items:
+                type: string
+                maxLength: 100
+              nullable: true
+              description: Categories from check metadata for efficient filtering
             raw_result: {}
             inserted_at:
               type: string
@@ -11229,10 +11573,15 @@ components:
               type: array
               items:
                 type: string
+            categories:
+              type: array
+              items:
+                type: string
           required:
           - services
           - regions
           - resource_types
+          - categories
     FindingMetadataResponse:
       type: object
       properties:
@@ -13935,6 +14284,24 @@ components:
           $ref: '#/components/schemas/OverviewSeverity'
       required:
       - data
+    PaginatedAttackSurfaceOverviewList:
+      type: object
+      properties:
+        data:
+          type: array
+          items:
+            $ref: '#/components/schemas/AttackSurfaceOverview'
+      required:
+      - data
+    PaginatedCategoryOverviewList:
+      type: object
+      properties:
+        data:
+          type: array
+          items:
+            $ref: '#/components/schemas/CategoryOverview'
+      required:
+      - data
     PaginatedComplianceOverviewAttributesList:
       type: object
       properties:

api/src/backend/api/tests/test_views.py

@@ -4267,6 +4267,74 @@ class TestFindingViewSet:
         assert attributes["regions"] == latest_scan_finding.resource_regions
         assert attributes["resource_types"] == latest_scan_finding.resource_types
 
+    def test_findings_metadata_categories(
+        self, authenticated_client, findings_with_categories
+    ):
+        finding = findings_with_categories
+        response = authenticated_client.get(
+            reverse("finding-metadata"),
+            {"filter[inserted_at]": finding.inserted_at.strftime("%Y-%m-%d")},
+        )
+        assert response.status_code == status.HTTP_200_OK
+        attributes = response.json()["data"]["attributes"]
+        assert set(attributes["categories"]) == {"gen-ai", "security"}
+
+    def test_findings_metadata_latest_categories(
+        self, authenticated_client, latest_scan_finding_with_categories
+    ):
+        response = authenticated_client.get(
+            reverse("finding-metadata_latest"),
+        )
+        assert response.status_code == status.HTTP_200_OK
+        attributes = response.json()["data"]["attributes"]
+        assert set(attributes["categories"]) == {"gen-ai", "iam"}
+
+    def test_findings_filter_by_category(
+        self, authenticated_client, findings_with_categories
+    ):
+        finding = findings_with_categories
+        response = authenticated_client.get(
+            reverse("finding-list"),
+            {
+                "filter[category]": "gen-ai",
+                "filter[inserted_at]": finding.inserted_at.strftime("%Y-%m-%d"),
+            },
+        )
+        assert response.status_code == status.HTTP_200_OK
+        assert len(response.json()["data"]) == 1
+        assert set(response.json()["data"][0]["attributes"]["categories"]) == {
+            "gen-ai",
+            "security",
+        }
+
+    def test_findings_filter_by_category_in(
+        self, authenticated_client, findings_with_multiple_categories
+    ):
+        finding1, _ = findings_with_multiple_categories
+        response = authenticated_client.get(
+            reverse("finding-list"),
+            {
+                "filter[category__in]": "gen-ai,iam",
+                "filter[inserted_at]": finding1.inserted_at.strftime("%Y-%m-%d"),
+            },
+        )
+        assert response.status_code == status.HTTP_200_OK
+        assert len(response.json()["data"]) == 2
+
+    def test_findings_filter_by_category_no_match(
+        self, authenticated_client, findings_with_categories
+    ):
+        finding = findings_with_categories
+        response = authenticated_client.get(
+            reverse("finding-list"),
+            {
+                "filter[category]": "nonexistent",
+                "filter[inserted_at]": finding.inserted_at.strftime("%Y-%m-%d"),
+            },
+        )
+        assert response.status_code == status.HTTP_200_OK
+        assert len(response.json()["data"]) == 0
+
 
 @pytest.mark.django_db
 class TestJWTFields:
@@ -7258,7 +7326,6 @@ class TestOverviewViewSet:
             assert item["attributes"]["total_findings"] == 0
             assert item["attributes"]["failed_findings"] == 0
             assert item["attributes"]["muted_failed_findings"] == 0
-            assert item["attributes"]["check_ids"] == []
 
     def test_overview_attack_surface_with_data(
         self,
@@ -7270,13 +7337,6 @@ class TestOverviewViewSet:
         tenant = tenants_fixture[0]
         provider = providers_fixture[0]
 
-        mapping = {
-            "internet-exposed": {"aws-check-1", "aws-check-2"},
-            "secrets": {"aws-secret-check"},
-            "privilege-escalation": {"aws-priv-check"},
-            "ec2-imdsv1": {"aws-imdsv1-check"},
-        }
-
         scan = Scan.objects.create(
             name="attack-surface-scan",
             provider=provider,
@@ -7302,11 +7362,7 @@ class TestOverviewViewSet:
             muted_failed=2,
         )
 
-        with patch(
-            "api.v1.views._get_attack_surface_mapping_from_provider",
-            return_value=mapping,
-        ):
-            response = authenticated_client.get(reverse("overview-attack-surface"))
+        response = authenticated_client.get(reverse("overview-attack-surface"))
         assert response.status_code == status.HTTP_200_OK
         data = response.json()["data"]
         assert len(data) == 4
@@ -7314,19 +7370,10 @@ class TestOverviewViewSet:
         results_by_type = {item["id"]: item["attributes"] for item in data}
         assert results_by_type["internet-exposed"]["total_findings"] == 20
         assert results_by_type["internet-exposed"]["failed_findings"] == 10
-        assert set(results_by_type["internet-exposed"]["check_ids"]) == {
-            "aws-check-1",
-            "aws-check-2",
-        }
         assert results_by_type["secrets"]["total_findings"] == 15
         assert results_by_type["secrets"]["failed_findings"] == 8
-        assert set(results_by_type["secrets"]["check_ids"]) == {"aws-secret-check"}
         assert results_by_type["privilege-escalation"]["total_findings"] == 0
-        assert set(results_by_type["privilege-escalation"]["check_ids"]) == {
-            "aws-priv-check"
-        }
         assert results_by_type["ec2-imdsv1"]["total_findings"] == 0
-        assert set(results_by_type["ec2-imdsv1"]["check_ids"]) == {"aws-imdsv1-check"}
 
     def test_overview_attack_surface_provider_filter(
         self,
@@ -7353,13 +7400,6 @@ class TestOverviewViewSet:
             tenant=tenant,
         )
 
-        mapping = {
-            "internet-exposed": {"shared-check", "shared-check"},
-            "secrets": set(),
-            "privilege-escalation": {"priv-check"},
-            "ec2-imdsv1": {"imdsv1-check"},
-        }
-
         create_attack_surface_overview(
             tenant,
             scan1,
@@ -7377,20 +7417,15 @@ class TestOverviewViewSet:
             muted_failed=3,
         )
 
-        with patch(
-            "api.v1.views._get_attack_surface_mapping_from_provider",
-            return_value=mapping,
-        ):
-            response = authenticated_client.get(
-                reverse("overview-attack-surface"),
-                {"filter[provider_id]": str(provider1.id)},
-            )
+        response = authenticated_client.get(
+            reverse("overview-attack-surface"),
+            {"filter[provider_id]": str(provider1.id)},
+        )
         assert response.status_code == status.HTTP_200_OK
         data = response.json()["data"]
         results_by_type = {item["id"]: item["attributes"] for item in data}
         assert results_by_type["internet-exposed"]["total_findings"] == 10
         assert results_by_type["internet-exposed"]["failed_findings"] == 5
-        assert results_by_type["internet-exposed"]["check_ids"] == ["shared-check"]
 
     def test_overview_services_region_filter(
         self, authenticated_client, scan_summaries_fixture
@@ -7633,6 +7668,219 @@ class TestOverviewViewSet:
         assert len(data) == 1
         assert data[0]["attributes"]["overall_score"] == "80.00"
 
+    def test_overview_categories_no_data(self, authenticated_client):
+        response = authenticated_client.get(reverse("overview-categories"))
+        assert response.status_code == status.HTTP_200_OK
+        assert response.json()["data"] == []
+
+    def test_overview_categories_aggregates_by_category_with_severity(
+        self,
+        authenticated_client,
+        tenants_fixture,
+        providers_fixture,
+        create_scan_category_summary,
+    ):
+        tenant = tenants_fixture[0]
+        provider = providers_fixture[0]
+
+        scan = Scan.objects.create(
+            name="categories-scan",
+            provider=provider,
+            trigger=Scan.TriggerChoices.MANUAL,
+            state=StateChoices.COMPLETED,
+            tenant=tenant,
+        )
+
+        create_scan_category_summary(
+            tenant,
+            scan,
+            "iam",
+            "high",
+            total_findings=20,
+            failed_findings=10,
+            new_failed_findings=5,
+        )
+        create_scan_category_summary(
+            tenant,
+            scan,
+            "iam",
+            "medium",
+            total_findings=15,
+            failed_findings=8,
+            new_failed_findings=3,
+        )
+        create_scan_category_summary(
+            tenant,
+            scan,
+            "encryption",
+            "critical",
+            total_findings=5,
+            failed_findings=2,
+            new_failed_findings=1,
+        )
+
+        response = authenticated_client.get(reverse("overview-categories"))
+        assert response.status_code == status.HTTP_200_OK
+        data = response.json()["data"]
+        assert len(data) == 2
+
+        results_by_category = {item["id"]: item["attributes"] for item in data}
+
+        assert results_by_category["iam"]["total_findings"] == 35
+        assert results_by_category["iam"]["failed_findings"] == 18
+        assert results_by_category["iam"]["new_failed_findings"] == 8
+        assert results_by_category["iam"]["severity"]["high"] == 10
+        assert results_by_category["iam"]["severity"]["medium"] == 8
+        assert results_by_category["iam"]["severity"]["critical"] == 0
+
+        assert results_by_category["encryption"]["total_findings"] == 5
+        assert results_by_category["encryption"]["failed_findings"] == 2
+        assert results_by_category["encryption"]["severity"]["critical"] == 2
+
+    @pytest.mark.parametrize(
+        "filter_key,filter_value_fn,expected_total,expected_failed",
+        [
+            ("filter[provider_id]", lambda p1, _: str(p1.id), 10, 5),
+            ("filter[provider_type]", lambda *_: "aws", 10, 5),
+            ("filter[provider_type__in]", lambda *_: "aws,gcp", 30, 20),
+        ],
+    )
+    def test_overview_categories_filters(
+        self,
+        authenticated_client,
+        tenants_fixture,
+        providers_fixture,
+        create_scan_category_summary,
+        filter_key,
+        filter_value_fn,
+        expected_total,
+        expected_failed,
+    ):
+        tenant = tenants_fixture[0]
+        provider1, _, gcp_provider, *_ = providers_fixture
+
+        scan1 = Scan.objects.create(
+            name="categories-scan-1",
+            provider=provider1,
+            trigger=Scan.TriggerChoices.MANUAL,
+            state=StateChoices.COMPLETED,
+            tenant=tenant,
+        )
+        scan2 = Scan.objects.create(
+            name="categories-scan-2",
+            provider=gcp_provider,
+            trigger=Scan.TriggerChoices.MANUAL,
+            state=StateChoices.COMPLETED,
+            tenant=tenant,
+        )
+
+        create_scan_category_summary(
+            tenant, scan1, "iam", "high", total_findings=10, failed_findings=5
+        )
+        create_scan_category_summary(
+            tenant, scan2, "iam", "high", total_findings=20, failed_findings=15
+        )
+
+        response = authenticated_client.get(
+            reverse("overview-categories"),
+            {filter_key: filter_value_fn(provider1, gcp_provider)},
+        )
+        assert response.status_code == status.HTTP_200_OK
+        data = response.json()["data"]
+        assert len(data) == 1
+        assert data[0]["attributes"]["total_findings"] == expected_total
+        assert data[0]["attributes"]["failed_findings"] == expected_failed
+
+    def test_overview_categories_category_filter(
+        self,
+        authenticated_client,
+        tenants_fixture,
+        providers_fixture,
+        create_scan_category_summary,
+    ):
+        tenant = tenants_fixture[0]
+        provider = providers_fixture[0]
+
+        scan = Scan.objects.create(
+            name="category-filter-scan",
+            provider=provider,
+            trigger=Scan.TriggerChoices.MANUAL,
+            state=StateChoices.COMPLETED,
+            tenant=tenant,
+        )
+
+        create_scan_category_summary(
+            tenant, scan, "iam", "high", total_findings=10, failed_findings=5
+        )
+        create_scan_category_summary(
+            tenant, scan, "encryption", "medium", total_findings=20, failed_findings=8
+        )
+        create_scan_category_summary(
+            tenant, scan, "logging", "low", total_findings=15, failed_findings=3
+        )
+
+        response = authenticated_client.get(
+            reverse("overview-categories"),
+            {"filter[category__in]": "iam,encryption"},
+        )
+        assert response.status_code == status.HTTP_200_OK
+        data = response.json()["data"]
+        category_ids = {item["id"] for item in data}
+        assert category_ids == {"iam", "encryption"}
+
+    def test_overview_categories_aggregates_multiple_providers(
+        self,
+        authenticated_client,
+        tenants_fixture,
+        providers_fixture,
+        create_scan_category_summary,
+    ):
+        tenant = tenants_fixture[0]
+        provider1, provider2, *_ = providers_fixture
+
+        scan1 = Scan.objects.create(
+            name="multi-provider-scan-1",
+            provider=provider1,
+            trigger=Scan.TriggerChoices.MANUAL,
+            state=StateChoices.COMPLETED,
+            tenant=tenant,
+        )
+        scan2 = Scan.objects.create(
+            name="multi-provider-scan-2",
+            provider=provider2,
+            trigger=Scan.TriggerChoices.MANUAL,
+            state=StateChoices.COMPLETED,
+            tenant=tenant,
+        )
+
+        create_scan_category_summary(
+            tenant,
+            scan1,
+            "iam",
+            "high",
+            total_findings=10,
+            failed_findings=5,
+            new_failed_findings=2,
+        )
+        create_scan_category_summary(
+            tenant,
+            scan2,
+            "iam",
+            "high",
+            total_findings=15,
+            failed_findings=8,
+            new_failed_findings=3,
+        )
+
+        response = authenticated_client.get(reverse("overview-categories"))
+        assert response.status_code == status.HTTP_200_OK
+        data = response.json()["data"]
+        assert len(data) == 1
+        assert data[0]["id"] == "iam"
+        assert data[0]["attributes"]["total_findings"] == 25
+        assert data[0]["attributes"]["failed_findings"] == 13
+        assert data[0]["attributes"]["new_failed_findings"] == 5
+
 
 @pytest.mark.django_db
 class TestScheduleViewSet:

api/src/backend/api/utils.py

@@ -382,10 +382,18 @@ def get_findings_metadata_no_aggregations(tenant_id: str, filtered_queryset):
     regions = sorted({region for region in aggregation["regions"] or [] if region})
     resource_types = sorted(set(aggregation["resource_types"] or []))
 
+    # Aggregate categories from findings
+    categories_set = set()
+    for categories_list in filtered_queryset.values_list("categories", flat=True):
+        if categories_list:
+            categories_set.update(categories_list)
+    categories = sorted(categories_set)
+
     result = {
         "services": services,
         "regions": regions,
         "resource_types": resource_types,
+        "categories": categories,
     }
 
     serializer = FindingMetadataSerializer(data=result)

api/src/backend/api/v1/serializers.py

@@ -1301,6 +1301,7 @@ class FindingSerializer(RLSSerializer):
             "severity",
             "check_id",
             "check_metadata",
+            "categories",
             "raw_result",
             "inserted_at",
             "updated_at",
@@ -1356,6 +1357,7 @@ class FindingMetadataSerializer(BaseSerializerV1):
     resource_types = serializers.ListField(
         child=serializers.CharField(), allow_empty=True
     )
+    categories = serializers.ListField(child=serializers.CharField(), allow_empty=True)
     # Temporarily disabled until we implement tag filtering in the UI
     # tags = serializers.JSONField(help_text="Tags are described as key-value pairs.")
 
@@ -2242,14 +2244,26 @@ class AttackSurfaceOverviewSerializer(BaseSerializerV1):
     total_findings = serializers.IntegerField()
     failed_findings = serializers.IntegerField()
     muted_failed_findings = serializers.IntegerField()
-    check_ids = serializers.ListField(
-        child=serializers.CharField(), allow_empty=True, default=list, read_only=True
-    )
 
     class JSONAPIMeta:
         resource_name = "attack-surface-overviews"
 
 
+class CategoryOverviewSerializer(BaseSerializerV1):
+    """Serializer for category overview aggregations."""
+
+    id = serializers.CharField(source="category")
+    total_findings = serializers.IntegerField()
+    failed_findings = serializers.IntegerField()
+    new_failed_findings = serializers.IntegerField()
+    severity = serializers.JSONField(
+        help_text="Severity breakdown: {informational, low, medium, high, critical}"
+    )
+
+    class JSONAPIMeta:
+        resource_name = "category-overviews"
+
+
 class OverviewRegionSerializer(serializers.Serializer):
     id = serializers.SerializerMethodField()
     provider_type = serializers.CharField()

api/src/backend/api/v1/views.py

@@ -74,7 +74,6 @@ from rest_framework_json_api.views import RelationshipView, Response
 from rest_framework_simplejwt.exceptions import InvalidToken, TokenError
 from tasks.beat import schedule_provider_scan
 from tasks.jobs.export import get_s3_client
-from tasks.jobs.scan import _get_attack_surface_mapping_from_provider
 from tasks.tasks import (
     backfill_compliance_summaries_task,
     backfill_scan_resource_summaries_task,
@@ -100,6 +99,7 @@ from api.db_utils import rls_transaction
 from api.exceptions import TaskFailedException
 from api.filters import (
     AttackSurfaceOverviewFilter,
+    CategoryOverviewFilter,
     ComplianceOverviewFilter,
     CustomDjangoFilterBackend,
     DailySeveritySummaryFilter,
@@ -157,6 +157,7 @@ from api.models import (
     SAMLDomainIndex,
     SAMLToken,
     Scan,
+    ScanCategorySummary,
     ScanSummary,
     SeverityChoices,
     StateChoices,
@@ -178,6 +179,7 @@ from api.uuid_utils import datetime_to_uuid7, uuid7_start
 from api.v1.mixins import DisablePaginationMixin, PaginateByPkMixin, TaskManagementMixin
 from api.v1.serializers import (
     AttackSurfaceOverviewSerializer,
+    CategoryOverviewSerializer,
     ComplianceOverviewAttributesSerializer,
     ComplianceOverviewDetailSerializer,
     ComplianceOverviewDetailThreatscoreSerializer,
@@ -357,7 +359,7 @@ class SchemaView(SpectacularAPIView):
 
     def get(self, request, *args, **kwargs):
         spectacular_settings.TITLE = "Prowler API"
-        spectacular_settings.VERSION = "1.16.1"
+        spectacular_settings.VERSION = "1.17.1"
         spectacular_settings.DESCRIPTION = (
             "Prowler API specification.\n\nThis file is auto-generated."
         )
@@ -2760,12 +2762,15 @@ class FindingViewSet(PaginateByPkMixin, BaseRLSViewSet):
 
         queryset = ResourceScanSummary.objects.filter(tenant_id=tenant_id)
         scan_based_filters = {}
+        category_scan_filters = {}  # Filters for ScanCategorySummary
 
         if scans := query_params.get("filter[scan__in]") or query_params.get(
             "filter[scan]"
         ):
-            queryset = queryset.filter(scan_id__in=scans.split(","))
-            scan_based_filters = {"id__in": scans.split(",")}
+            scan_ids_list = scans.split(",")
+            queryset = queryset.filter(scan_id__in=scan_ids_list)
+            scan_based_filters = {"id__in": scan_ids_list}
+            category_scan_filters = {"scan_id__in": scan_ids_list}
         else:
             exact = query_params.get("filter[inserted_at]")
             gte = query_params.get("filter[inserted_at__gte]")
@@ -2809,6 +2814,7 @@ class FindingViewSet(PaginateByPkMixin, BaseRLSViewSet):
                 scan_based_filters = {
                     key.lstrip("scan_"): value for key, value in date_filters.items()
                 }
+                category_scan_filters = date_filters
 
         # ToRemove: Temporary fallback mechanism
         if not queryset.exists():
@@ -2855,10 +2861,31 @@ class FindingViewSet(PaginateByPkMixin, BaseRLSViewSet):
             .order_by("resource_type")
         )
 
+        # Get categories from ScanCategorySummary using same scan filters
+        categories = list(
+            ScanCategorySummary.objects.filter(
+                tenant_id=tenant_id, **category_scan_filters
+            )
+            .values_list("category", flat=True)
+            .distinct()
+            .order_by("category")
+        )
+
+        # Fallback to finding aggregation if no ScanCategorySummary exists
+        if not categories:
+            categories_set = set()
+            for categories_list in filtered_queryset.values_list(
+                "categories", flat=True
+            ):
+                if categories_list:
+                    categories_set.update(categories_list)
+            categories = sorted(categories_set)
+
         result = {
             "services": services,
             "regions": regions,
             "resource_types": resource_types,
+            "categories": categories,
         }
 
         serializer = self.get_serializer(data=result)
@@ -2963,10 +2990,36 @@ class FindingViewSet(PaginateByPkMixin, BaseRLSViewSet):
             .order_by("resource_type")
         )
 
+        # Get categories from ScanCategorySummary for latest scans
+        categories = list(
+            ScanCategorySummary.objects.filter(
+                tenant_id=tenant_id,
+                scan_id__in=latest_scans_queryset.values_list("id", flat=True),
+            )
+            .values_list("category", flat=True)
+            .distinct()
+            .order_by("category")
+        )
+
+        # Fallback to finding aggregation if no ScanCategorySummary exists
+        if not categories:
+            filtered_queryset = self.filter_queryset(self.get_queryset()).filter(
+                tenant_id=tenant_id,
+                scan_id__in=latest_scans_queryset.values_list("id", flat=True),
+            )
+            categories_set = set()
+            for categories_list in filtered_queryset.values_list(
+                "categories", flat=True
+            ):
+                if categories_list:
+                    categories_set.update(categories_list)
+            categories = sorted(categories_set)
+
         result = {
             "services": services,
             "regions": regions,
             "resource_types": resource_types,
+            "categories": categories,
         }
 
         serializer = self.get_serializer(data=result)
@@ -4026,32 +4079,19 @@ class ComplianceOverviewViewSet(BaseRLSViewSet, TaskManagementMixin):
         summary="Get attack surface overview",
         description="Retrieve aggregated attack surface metrics from latest completed scans per provider.",
         tags=["Overview"],
-        parameters=[
-            OpenApiParameter(
-                name="filter[provider_id]",
-                type=OpenApiTypes.UUID,
-                location=OpenApiParameter.QUERY,
-                description="Filter by specific provider ID",
-            ),
-            OpenApiParameter(
-                name="filter[provider_id.in]",
-                type=OpenApiTypes.STR,
-                location=OpenApiParameter.QUERY,
-                description="Filter by multiple provider IDs (comma-separated UUIDs)",
-            ),
-            OpenApiParameter(
-                name="filter[provider_type]",
-                type=OpenApiTypes.STR,
-                location=OpenApiParameter.QUERY,
-                description="Filter by provider type (aws, azure, gcp, etc.)",
-            ),
-            OpenApiParameter(
-                name="filter[provider_type.in]",
-                type=OpenApiTypes.STR,
-                location=OpenApiParameter.QUERY,
-                description="Filter by multiple provider types (comma-separated)",
-            ),
-        ],
+        filters=True,
+        responses={200: AttackSurfaceOverviewSerializer(many=True)},
+    ),
+    categories=extend_schema(
+        summary="Get category overview",
+        description=(
+            "Retrieve aggregated category metrics from latest completed scans per provider. "
+            "Returns one row per category with total, failed, and new failed findings counts, "
+            "plus a severity breakdown showing failed findings per severity level. "
+        ),
+        tags=["Overview"],
+        filters=True,
+        responses={200: CategoryOverviewSerializer(many=True)},
     ),
 )
 @method_decorator(CACHE_DECORATOR, name="list")
@@ -4100,6 +4140,8 @@ class OverviewViewSet(BaseRLSViewSet):
             return ThreatScoreSnapshotSerializer
         elif self.action == "attack_surface":
             return AttackSurfaceOverviewSerializer
+        elif self.action == "categories":
+            return CategoryOverviewSerializer
         return super().get_serializer_class()
 
     def get_filterset_class(self):
@@ -4111,6 +4153,10 @@ class OverviewViewSet(BaseRLSViewSet):
             return ScanSummarySeverityFilter
         elif self.action == "findings_severity_timeseries":
             return DailySeveritySummaryFilter
+        elif self.action == "categories":
+            return CategoryOverviewFilter
+        elif self.action == "attack_surface":
+            return AttackSurfaceOverviewFilter
         return None
 
     def filter_queryset(self, queryset):
@@ -4196,29 +4242,41 @@ class OverviewViewSet(BaseRLSViewSet):
         filterset = filterset_class(normalized_params, queryset=queryset)
         return filterset.qs
 
-    def _latest_scan_ids_for_allowed_providers(self, tenant_id):
+    def _latest_scan_ids_for_allowed_providers(self, tenant_id, provider_filters=None):
         provider_filter = self._get_provider_filter()
+        queryset = Scan.all_objects.filter(
+            tenant_id=tenant_id, state=StateChoices.COMPLETED, **provider_filter
+        )
+        if provider_filters:
+            queryset = queryset.filter(**provider_filters)
         return (
-            Scan.all_objects.filter(
-                tenant_id=tenant_id, state=StateChoices.COMPLETED, **provider_filter
-            )
-            .order_by("provider_id", "-inserted_at")
+            queryset.order_by("provider_id", "-inserted_at")
             .distinct("provider_id")
             .values_list("id", flat=True)
         )
 
-    def _attack_surface_check_ids_by_provider_types(self, provider_types):
-        check_ids_by_type = {
-            attack_surface_type: set()
-            for attack_surface_type in AttackSurfaceOverview.AttackSurfaceTypeChoices.values
-        }
-        for provider_type in provider_types:
-            attack_surface_mapping = _get_attack_surface_mapping_from_provider(
-                provider_type=provider_type
-            )
-            for attack_surface_type, check_ids in attack_surface_mapping.items():
-                check_ids_by_type[attack_surface_type].update(check_ids)
-        return check_ids_by_type
+    def _extract_provider_filters_from_params(self):
+        """Extract provider filters from query params to apply on Scan queryset."""
+        params = self.request.query_params
+        filters = {}
+
+        provider_id = params.get("filter[provider_id]")
+        if provider_id:
+            filters["provider_id"] = provider_id
+
+        provider_id_in = params.get("filter[provider_id__in]")
+        if provider_id_in:
+            filters["provider_id__in"] = provider_id_in.split(",")
+
+        provider_type = params.get("filter[provider_type]")
+        if provider_type:
+            filters["provider__provider"] = provider_type
+
+        provider_type_in = params.get("filter[provider_type__in]")
+        if provider_type_in:
+            filters["provider__provider__in"] = provider_type_in.split(",")
+
+        return filters
 
     @action(detail=False, methods=["get"], url_name="providers")
     def providers(self, request):
@@ -4825,22 +4883,13 @@ class OverviewViewSet(BaseRLSViewSet):
         tenant_id = request.tenant_id
         latest_scan_ids = self._latest_scan_ids_for_allowed_providers(tenant_id)
 
-        # Build base queryset and apply user filters via FilterSet
         base_queryset = AttackSurfaceOverview.objects.filter(
             tenant_id=tenant_id, scan_id__in=latest_scan_ids
         )
         filtered_queryset = self._apply_filterset(
             base_queryset, AttackSurfaceOverviewFilter
         )
-        provider_types = list(
-            filtered_queryset.values_list(
-                "scan__provider__provider", flat=True
-            ).distinct()
-        )
-        attack_surface_check_ids = self._attack_surface_check_ids_by_provider_types(
-            provider_types
-        )
-        # Aggregate attack surface data
+
         aggregation = filtered_queryset.values("attack_surface_type").annotate(
             total_findings=Coalesce(Sum("total_findings"), 0),
             failed_findings=Coalesce(Sum("failed_findings"), 0),
@@ -4863,12 +4912,71 @@ class OverviewViewSet(BaseRLSViewSet):
             }
 
         response_data = [
-            {
-                "attack_surface_type": key,
-                **value,
-                "check_ids": attack_surface_check_ids.get(key, []),
+            {"attack_surface_type": key, **value} for key, value in results.items()
+        ]
+
+        return Response(
+            self.get_serializer(response_data, many=True).data,
+            status=status.HTTP_200_OK,
+        )
+
+    @action(detail=False, methods=["get"], url_name="categories")
+    def categories(self, request):
+        tenant_id = request.tenant_id
+        provider_filters = self._extract_provider_filters_from_params()
+        latest_scan_ids = self._latest_scan_ids_for_allowed_providers(
+            tenant_id, provider_filters
+        )
+
+        base_queryset = ScanCategorySummary.objects.filter(
+            tenant_id=tenant_id, scan_id__in=latest_scan_ids
+        )
+        provider_filter_keys = {
+            "provider_id",
+            "provider_id__in",
+            "provider_type",
+            "provider_type__in",
+        }
+        filtered_queryset = self._apply_filterset(
+            base_queryset, CategoryOverviewFilter, exclude_keys=provider_filter_keys
+        )
+
+        aggregation = (
+            filtered_queryset.values("category", "severity")
+            .annotate(
+                total=Coalesce(Sum("total_findings"), 0),
+                failed=Coalesce(Sum("failed_findings"), 0),
+                new_failed=Coalesce(Sum("new_failed_findings"), 0),
+            )
+            .order_by("category", "severity")
+        )
+
+        category_data = defaultdict(
+            lambda: {
+                "total_findings": 0,
+                "failed_findings": 0,
+                "new_failed_findings": 0,
+                "severity": {
+                    "informational": 0,
+                    "low": 0,
+                    "medium": 0,
+                    "high": 0,
+                    "critical": 0,
+                },
             }
-            for key, value in results.items()
+        )
+
+        for row in aggregation:
+            cat = row["category"]
+            sev = row["severity"]
+            category_data[cat]["total_findings"] += row["total"]
+            category_data[cat]["failed_findings"] += row["failed"]
+            category_data[cat]["new_failed_findings"] += row["new_failed"]
+            if sev in category_data[cat]["severity"]:
+                category_data[cat]["severity"][sev] = row["failed"]
+
+        response_data = [
+            {"category": cat, **data} for cat, data in sorted(category_data.items())
         ]
 
         return Response(

api/src/backend/config/guniconf.py

@@ -19,8 +19,6 @@ PORT = env("DJANGO_PORT", default=8000)
 
 # Server settings
 bind = f"{BIND_ADDRESS}:{PORT}"
-# TODO: Remove after the category filter is implemented
-limit_request_line = 0
 
 workers = env.int("DJANGO_WORKERS", default=multiprocessing.cpu_count() * 2 + 1)
 reload = DEBUG

api/src/backend/conftest.py

@@ -11,7 +11,10 @@ from django.urls import reverse
 from django_celery_results.models import TaskResult
 from rest_framework import status
 from rest_framework.test import APIClient
-from tasks.jobs.backfill import backfill_resource_scan_summaries
+from tasks.jobs.backfill import (
+    backfill_resource_scan_summaries,
+    backfill_scan_category_summaries,
+)
 
 from api.db_utils import rls_transaction
 from api.models import (
@@ -36,6 +39,7 @@ from api.models import (
     SAMLConfiguration,
     SAMLDomainIndex,
     Scan,
+    ScanCategorySummary,
     ScanSummary,
     StateChoices,
     StatusChoices,
@@ -1271,6 +1275,113 @@ def latest_scan_finding(authenticated_client, providers_fixture, resources_fixtu
     return finding
 
 
+@pytest.fixture(scope="function")
+def findings_with_categories(scans_fixture, resources_fixture):
+    scan = scans_fixture[0]
+    resource = resources_fixture[0]
+
+    finding = Finding.objects.create(
+        tenant_id=scan.tenant_id,
+        uid="finding_with_categories_1",
+        scan=scan,
+        delta=None,
+        status=Status.FAIL,
+        status_extended="test status",
+        impact=Severity.critical,
+        impact_extended="test impact",
+        severity=Severity.critical,
+        raw_result={"status": Status.FAIL},
+        check_id="genai_check",
+        check_metadata={"CheckId": "genai_check"},
+        categories=["gen-ai", "security"],
+        first_seen_at="2024-01-02T00:00:00Z",
+    )
+    finding.add_resources([resource])
+    backfill_resource_scan_summaries(str(scan.tenant_id), str(scan.id))
+    return finding
+
+
+@pytest.fixture(scope="function")
+def findings_with_multiple_categories(scans_fixture, resources_fixture):
+    scan = scans_fixture[0]
+    resource1, resource2 = resources_fixture[:2]
+
+    finding1 = Finding.objects.create(
+        tenant_id=scan.tenant_id,
+        uid="finding_multi_cat_1",
+        scan=scan,
+        delta=None,
+        status=Status.FAIL,
+        status_extended="test status",
+        impact=Severity.critical,
+        impact_extended="test impact",
+        severity=Severity.critical,
+        raw_result={"status": Status.FAIL},
+        check_id="genai_check",
+        check_metadata={"CheckId": "genai_check"},
+        categories=["gen-ai", "security"],
+        first_seen_at="2024-01-02T00:00:00Z",
+    )
+    finding1.add_resources([resource1])
+
+    finding2 = Finding.objects.create(
+        tenant_id=scan.tenant_id,
+        uid="finding_multi_cat_2",
+        scan=scan,
+        delta=None,
+        status=Status.FAIL,
+        status_extended="test status 2",
+        impact=Severity.high,
+        impact_extended="test impact 2",
+        severity=Severity.high,
+        raw_result={"status": Status.FAIL},
+        check_id="iam_check",
+        check_metadata={"CheckId": "iam_check"},
+        categories=["iam", "security"],
+        first_seen_at="2024-01-02T00:00:00Z",
+    )
+    finding2.add_resources([resource2])
+
+    backfill_resource_scan_summaries(str(scan.tenant_id), str(scan.id))
+    return finding1, finding2
+
+
+@pytest.fixture(scope="function")
+def latest_scan_finding_with_categories(
+    authenticated_client, providers_fixture, resources_fixture
+):
+    provider = providers_fixture[0]
+    tenant_id = str(providers_fixture[0].tenant_id)
+    resource = resources_fixture[0]
+    scan = Scan.objects.create(
+        name="latest completed scan with categories",
+        provider=provider,
+        trigger=Scan.TriggerChoices.MANUAL,
+        state=StateChoices.COMPLETED,
+        tenant_id=tenant_id,
+    )
+    finding = Finding.objects.create(
+        tenant_id=tenant_id,
+        uid="latest_finding_with_categories",
+        scan=scan,
+        delta="new",
+        status=Status.FAIL,
+        status_extended="test status",
+        impact=Severity.critical,
+        impact_extended="test impact",
+        severity=Severity.critical,
+        raw_result={"status": Status.FAIL},
+        check_id="genai_iam_check",
+        check_metadata={"CheckId": "genai_iam_check"},
+        categories=["gen-ai", "iam"],
+        first_seen_at="2024-01-02T00:00:00Z",
+    )
+    finding.add_resources([resource])
+    backfill_resource_scan_summaries(tenant_id, str(scan.id))
+    backfill_scan_category_summaries(tenant_id, str(scan.id))
+    return finding
+
+
 @pytest.fixture(scope="function")
 def latest_scan_resource(authenticated_client, providers_fixture):
     provider = providers_fixture[0]
@@ -1485,6 +1596,30 @@ def create_attack_surface_overview():
     return _create
 
 
+@pytest.fixture
+def create_scan_category_summary():
+    def _create(
+        tenant,
+        scan,
+        category,
+        severity,
+        total_findings=10,
+        failed_findings=5,
+        new_failed_findings=2,
+    ):
+        return ScanCategorySummary.objects.create(
+            tenant=tenant,
+            scan=scan,
+            category=category,
+            severity=severity,
+            total_findings=total_findings,
+            failed_findings=failed_findings,
+            new_failed_findings=new_failed_findings,
+        )
+
+    return _create
+
+
 def get_authorization_header(access_token: str) -> dict:
     return {"Authorization": f"Bearer {access_token}"}
 

api/src/backend/tasks/beat.py

@@ -61,5 +61,5 @@ def schedule_provider_scan(provider_instance: Provider):
             "tenant_id": str(provider_instance.tenant_id),
             "provider_id": provider_id,
         },
-        countdown=1,  # Avoid race conditions between the worker and the database
+        countdown=5,  # Avoid race conditions between the worker and the database
     )

api/src/backend/tasks/jobs/backfill.py

@@ -3,6 +3,7 @@ from datetime import timedelta
 
 from django.db.models import Sum
 from django.utils import timezone
+from tasks.jobs.scan import aggregate_category_counts
 
 from api.db_router import READ_REPLICA_ALIAS
 from api.db_utils import rls_transaction
@@ -10,10 +11,12 @@ from api.models import (
     ComplianceOverviewSummary,
     ComplianceRequirementOverview,
     DailySeveritySummary,
+    Finding,
     Resource,
     ResourceFindingMapping,
     ResourceScanSummary,
     Scan,
+    ScanCategorySummary,
     ScanSummary,
     StateChoices,
 )
@@ -274,3 +277,67 @@ def backfill_daily_severity_summaries(tenant_id: str, days: int = None):
         "updated": updated_count,
         "total_days": len(latest_scans_by_day),
     }
+
+
+def backfill_scan_category_summaries(tenant_id: str, scan_id: str):
+    """
+    Backfill ScanCategorySummary for a completed scan.
+
+    Aggregates category counts from all findings in the scan and creates
+    one ScanCategorySummary row per (category, severity) combination.
+
+    Args:
+        tenant_id: Target tenant UUID
+        scan_id: Scan UUID to backfill
+
+    Returns:
+        dict: Status indicating whether backfill was performed
+    """
+    with rls_transaction(tenant_id, using=READ_REPLICA_ALIAS):
+        if ScanCategorySummary.objects.filter(
+            tenant_id=tenant_id, scan_id=scan_id
+        ).exists():
+            return {"status": "already backfilled"}
+
+        if not Scan.objects.filter(
+            tenant_id=tenant_id,
+            id=scan_id,
+            state__in=(StateChoices.COMPLETED, StateChoices.FAILED),
+        ).exists():
+            return {"status": "scan is not completed"}
+
+        category_counts: dict[tuple[str, str], dict[str, int]] = {}
+        for finding in Finding.all_objects.filter(
+            tenant_id=tenant_id, scan_id=scan_id
+        ).values("categories", "severity", "status", "delta", "muted"):
+            aggregate_category_counts(
+                categories=finding.get("categories") or [],
+                severity=finding.get("severity"),
+                status=finding.get("status"),
+                delta=finding.get("delta"),
+                muted=finding.get("muted", False),
+                cache=category_counts,
+            )
+
+        if not category_counts:
+            return {"status": "no categories to backfill"}
+
+    category_summaries = [
+        ScanCategorySummary(
+            tenant_id=tenant_id,
+            scan_id=scan_id,
+            category=category,
+            severity=severity,
+            total_findings=counts["total"],
+            failed_findings=counts["failed"],
+            new_failed_findings=counts["new_failed"],
+        )
+        for (category, severity), counts in category_counts.items()
+    ]
+
+    with rls_transaction(tenant_id):
+        ScanCategorySummary.objects.bulk_create(
+            category_summaries, batch_size=500, ignore_conflicts=True
+        )
+
+    return {"status": "backfilled", "categories_count": len(category_counts)}

api/src/backend/tasks/jobs/lighthouse_providers.py

@@ -11,6 +11,41 @@ from api.models import LighthouseProviderConfiguration, LighthouseProviderModels
 
 logger = get_task_logger(__name__)
 
+# OpenAI model prefixes to exclude from Lighthouse model selection.
+# These models don't support text chat completions and tool calling.
+EXCLUDED_OPENAI_MODEL_PREFIXES = (
+    "dall-e",  # Image generation
+    "whisper",  # Audio transcription
+    "tts-",  # Text-to-speech (tts-1, tts-1-hd, etc.)
+    "sora",  # Text-to-video (sora-2, sora-2-pro, etc.)
+    "text-embedding",  # Embeddings
+    "embedding",  # Embeddings (alternative naming)
+    "text-moderation",  # Content moderation
+    "omni-moderation",  # Content moderation
+    "text-davinci",  # Legacy completion models
+    "text-curie",  # Legacy completion models
+    "text-babbage",  # Legacy completion models
+    "text-ada",  # Legacy completion models
+    "davinci",  # Legacy completion models
+    "curie",  # Legacy completion models
+    "babbage",  # Legacy completion models
+    "ada",  # Legacy completion models
+    "computer-use",  # Computer control agent
+    "gpt-image",  # Image generation
+    "gpt-audio",  # Audio models
+    "gpt-realtime",  # Realtime voice API
+)
+
+# OpenAI model substrings to exclude (patterns that can appear anywhere in model ID).
+# These patterns identify non-chat model variants.
+EXCLUDED_OPENAI_MODEL_SUBSTRINGS = (
+    "-audio-",  # Audio preview models (gpt-4o-audio-preview, etc.)
+    "-realtime-",  # Realtime preview models (gpt-4o-realtime-preview, etc.)
+    "-transcribe",  # Transcription models (gpt-4o-transcribe, etc.)
+    "-tts",  # TTS models (gpt-4o-mini-tts)
+    "-instruct",  # Legacy instruct models (gpt-3.5-turbo-instruct, etc.)
+)
+
 
 def _extract_error_message(e: Exception) -> str:
     """
@@ -283,20 +318,41 @@ def _fetch_openai_models(api_key: str) -> Dict[str, str]:
     """
     Fetch available models from OpenAI API.
 
+    Filters out models that don't support text input/output and tool calling,
+    such as image generation (DALL-E), audio transcription (Whisper),
+    text-to-speech (TTS), embeddings, and moderation models.
+
     Args:
         api_key: OpenAI API key for authentication.
 
     Returns:
         Dict mapping model_id to model_name. For OpenAI, both are the same
-        as the API doesn't provide separate display names.
+        as the API doesn't provide separate display names. Only includes
+        models that support text input, text output or tool calling.
 
     Raises:
         Exception: If the API call fails.
     """
     client = openai.OpenAI(api_key=api_key)
     models = client.models.list()
-    # OpenAI uses model.id for both ID and display name
-    return {m.id: m.id for m in getattr(models, "data", [])}
+
+    # Filter models to only include those supporting chat completions + tool calling
+    filtered_models = {}
+    for model in getattr(models, "data", []):
+        model_id = model.id
+
+        # Skip if model ID starts with excluded prefixes
+        if model_id.startswith(EXCLUDED_OPENAI_MODEL_PREFIXES):
+            continue
+
+        # Skip if model ID contains excluded substrings
+        if any(substring in model_id for substring in EXCLUDED_OPENAI_MODEL_SUBSTRINGS):
+            continue
+
+        # Include model (supports chat completions + tool calling)
+        filtered_models[model_id] = model_id
+
+    return filtered_models
 
 
 def _fetch_openai_compatible_models(base_url: str, api_key: str) -> Dict[str, str]:

api/src/backend/tasks/jobs/report.py

@@ -243,15 +243,28 @@ def _safe_getattr(obj, attr: str, default: str = "N/A") -> str:
 
 
 def _create_info_table_style() -> TableStyle:
-    """Create a reusable table style for information/metadata tables."""
+    """Create a reusable table style for information/metadata tables.
+
+    ReportLab TableStyle coordinate system:
+        - Format: (COMMAND, (start_col, start_row), (end_col, end_row), value)
+        - Coordinates use (column, row) format, starting at (0, 0) for top-left cell
+        - Negative indices work like Python slicing: -1 means "last row/column"
+        - (0, 0) to (0, -1) = entire first column (all rows)
+        - (0, 0) to (-1, 0) = entire first row (all columns)
+        - (0, 0) to (-1, -1) = entire table
+        - Styles are applied in order; later rules override earlier ones
+    """
     return TableStyle(
         [
+            # Column 0 (labels): blue background with white text
             ("BACKGROUND", (0, 0), (0, -1), COLOR_BLUE),
             ("TEXTCOLOR", (0, 0), (0, -1), COLOR_WHITE),
             ("FONTNAME", (0, 0), (0, -1), "FiraCode"),
+            # Column 1 (values): light blue background with gray text
             ("BACKGROUND", (1, 0), (1, -1), COLOR_BG_BLUE),
             ("TEXTCOLOR", (1, 0), (1, -1), COLOR_GRAY),
             ("FONTNAME", (1, 0), (1, -1), "PlusJakartaSans"),
+            # Apply to entire table
             ("ALIGN", (0, 0), (-1, -1), "LEFT"),
             ("VALIGN", (0, 0), (-1, -1), "TOP"),
             ("FONTSIZE", (0, 0), (-1, -1), 11),
@@ -265,19 +278,30 @@ def _create_info_table_style() -> TableStyle:
 
 
 def _create_header_table_style(header_color: colors.Color = None) -> TableStyle:
-    """Create a reusable table style for tables with headers."""
+    """Create a reusable table style for tables with headers.
+
+    ReportLab TableStyle coordinate system:
+        - Format: (COMMAND, (start_col, start_row), (end_col, end_row), value)
+        - (0, 0) to (-1, 0) = entire first row (header row)
+        - (1, 1) to (-1, -1) = all data cells (excludes header row and first column)
+        - See _create_info_table_style() for full coordinate system documentation
+    """
     if header_color is None:
         header_color = COLOR_BLUE
 
     return TableStyle(
         [
+            # Header row (row 0): colored background with white text
             ("BACKGROUND", (0, 0), (-1, 0), header_color),
             ("TEXTCOLOR", (0, 0), (-1, 0), COLOR_WHITE),
             ("FONTNAME", (0, 0), (-1, 0), "FiraCode"),
             ("FONTSIZE", (0, 0), (-1, 0), 10),
+            # Apply to entire table
             ("ALIGN", (0, 0), (-1, -1), "CENTER"),
             ("VALIGN", (0, 0), (-1, -1), "MIDDLE"),
+            # Data cells (excluding header): smaller font
             ("FONTSIZE", (1, 1), (-1, -1), 9),
+            # Apply to entire table
             ("GRID", (0, 0), (-1, -1), 1, COLOR_GRID_GRAY),
             ("LEFTPADDING", (0, 0), (-1, -1), PADDING_MEDIUM),
             ("RIGHTPADDING", (0, 0), (-1, -1), PADDING_MEDIUM),
@@ -288,18 +312,30 @@ def _create_header_table_style(header_color: colors.Color = None) -> TableStyle:
 
 
 def _create_findings_table_style() -> TableStyle:
-    """Create a reusable table style for findings tables."""
+    """Create a reusable table style for findings tables.
+
+    ReportLab TableStyle coordinate system:
+        - Format: (COMMAND, (start_col, start_row), (end_col, end_row), value)
+        - (0, 0) to (-1, 0) = entire first row (header row)
+        - (0, 0) to (0, 0) = only the top-left cell
+        - See _create_info_table_style() for full coordinate system documentation
+    """
     return TableStyle(
         [
+            # Header row (row 0): colored background with white text
             ("BACKGROUND", (0, 0), (-1, 0), COLOR_BLUE),
             ("TEXTCOLOR", (0, 0), (-1, 0), COLOR_WHITE),
             ("FONTNAME", (0, 0), (-1, 0), "FiraCode"),
+            # Only top-left cell centered (for index/number column)
             ("ALIGN", (0, 0), (0, 0), "CENTER"),
+            # Apply to entire table
             ("VALIGN", (0, 0), (-1, -1), "MIDDLE"),
             ("FONTSIZE", (0, 0), (-1, -1), 9),
             ("GRID", (0, 0), (-1, -1), 0.1, COLOR_BORDER_GRAY),
+            # Remove padding only from top-left cell
             ("LEFTPADDING", (0, 0), (0, 0), 0),
             ("RIGHTPADDING", (0, 0), (0, 0), 0),
+            # Apply to entire table
             ("TOPPADDING", (0, 0), (-1, -1), PADDING_SMALL),
             ("BOTTOMPADDING", (0, 0), (-1, -1), PADDING_SMALL),
         ]
@@ -1103,11 +1139,15 @@ def generate_threatscore_report(
         elements.append(Spacer(1, 0.5 * inch))
 
         # Add compliance information table
+        provider_alias = provider_obj.alias or "N/A"
         info_data = [
             ["Framework:", compliance_framework],
             ["ID:", compliance_id],
             ["Name:", Paragraph(compliance_name, normal_center)],
             ["Version:", compliance_version],
+            ["Provider:", provider_type.upper()],
+            ["Account ID:", provider_obj.uid],
+            ["Alias:", provider_alias],
             ["Scan ID:", scan_id],
             ["Description:", Paragraph(compliance_description, normal_center)],
         ]
@@ -2059,12 +2099,15 @@ def generate_ens_report(
         elements.append(Spacer(1, 0.5 * inch))
 
         # Add compliance information table
+        provider_alias = provider_obj.alias or "N/A"
         info_data = [
             ["Framework:", compliance_framework],
             ["ID:", compliance_id],
             ["Nombre:", Paragraph(compliance_name, normal_center)],
             ["Versión:", compliance_version],
             ["Proveedor:", provider_type.upper()],
+            ["Account ID:", provider_obj.uid],
+            ["Alias:", provider_alias],
             ["Scan ID:", scan_id],
             ["Descripción:", Paragraph(compliance_description, normal_center)],
         ]
@@ -2072,12 +2115,12 @@ def generate_ens_report(
         info_table.setStyle(
             TableStyle(
                 [
-                    ("BACKGROUND", (0, 0), (0, 6), colors.Color(0.2, 0.4, 0.6)),
-                    ("TEXTCOLOR", (0, 0), (0, 6), colors.white),
-                    ("FONTNAME", (0, 0), (0, 6), "FiraCode"),
-                    ("BACKGROUND", (1, 0), (1, 6), colors.Color(0.95, 0.97, 1.0)),
-                    ("TEXTCOLOR", (1, 0), (1, 6), colors.Color(0.2, 0.2, 0.2)),
-                    ("FONTNAME", (1, 0), (1, 6), "PlusJakartaSans"),
+                    ("BACKGROUND", (0, 0), (0, -1), colors.Color(0.2, 0.4, 0.6)),
+                    ("TEXTCOLOR", (0, 0), (0, -1), colors.white),
+                    ("FONTNAME", (0, 0), (0, -1), "FiraCode"),
+                    ("BACKGROUND", (1, 0), (1, -1), colors.Color(0.95, 0.97, 1.0)),
+                    ("TEXTCOLOR", (1, 0), (1, -1), colors.Color(0.2, 0.2, 0.2)),
+                    ("FONTNAME", (1, 0), (1, -1), "PlusJakartaSans"),
                     ("ALIGN", (0, 0), (-1, -1), "LEFT"),
                     ("VALIGN", (0, 0), (-1, -1), "TOP"),
                     ("FONTSIZE", (0, 0), (-1, -1), 11),
@@ -2997,11 +3040,14 @@ def generate_nis2_report(
         elements.append(Spacer(1, 0.3 * inch))
 
         # Compliance metadata table
+        provider_alias = provider_obj.alias or "N/A"
         metadata_data = [
             ["Framework:", compliance_framework],
             ["Name:", Paragraph(compliance_name, normal_center)],
             ["Version:", compliance_version or "N/A"],
             ["Provider:", provider_type.upper()],
+            ["Account ID:", provider_obj.uid],
+            ["Alias:", provider_alias],
             ["Scan ID:", scan_id],
             ["Description:", Paragraph(compliance_description, normal_center)],
         ]

api/src/backend/tasks/jobs/scan.py

@@ -8,6 +8,7 @@ from collections import defaultdict
 from datetime import datetime, timezone
 from typing import Any
 
+import sentry_sdk
 from celery.utils.log import get_task_logger
 from config.env import env
 from config.settings.celery import CELERY_DEADLOCK_ATTEMPTS
@@ -39,6 +40,7 @@ from api.models import (
     ResourceScanSummary,
     ResourceTag,
     Scan,
+    ScanCategorySummary,
     ScanSummary,
     StateChoices,
 )
@@ -77,7 +79,6 @@ FINDINGS_MICRO_BATCH_SIZE = env.int("DJANGO_FINDINGS_MICRO_BATCH_SIZE", default=
 # Controls how many rows each ORM bulk_create/bulk_update call sends to Postgres
 SCAN_DB_BATCH_SIZE = env.int("DJANGO_SCAN_DB_BATCH_SIZE", default=500)
 
-
 ATTACK_SURFACE_PROVIDER_COMPATIBILITY = {
     "internet-exposed": None,  # Compatible with all providers
     "secrets": None,  # Compatible with all providers
@@ -88,6 +89,40 @@ ATTACK_SURFACE_PROVIDER_COMPATIBILITY = {
 _ATTACK_SURFACE_MAPPING_CACHE: dict[str, dict] = {}
 
 
+def aggregate_category_counts(
+    categories: list[str],
+    severity: str,
+    status: str,
+    delta: str | None,
+    muted: bool,
+    cache: dict[tuple[str, str], dict[str, int]],
+) -> None:
+    """
+    Increment category counters in-place for a finding.
+
+    Args:
+        categories: List of categories from finding metadata.
+        severity: Severity level (e.g., "high", "medium").
+        status: Finding status as string ("FAIL", "PASS").
+        delta: Delta value as string ("new", "changed") or None.
+        muted: Whether the finding is muted.
+        cache: Dict {(category, severity): {"total", "failed", "new_failed"}} to update.
+    """
+    is_failed = status == "FAIL" and not muted
+    is_new_failed = is_failed and delta == "new"
+
+    for cat in categories:
+        key = (cat, severity)
+        if key not in cache:
+            cache[key] = {"total": 0, "failed": 0, "new_failed": 0}
+        if not muted:
+            cache[key]["total"] += 1
+        if is_failed:
+            cache[key]["failed"] += 1
+        if is_new_failed:
+            cache[key]["new_failed"] += 1
+
+
 def _get_attack_surface_mapping_from_provider(provider_type: str) -> dict:
     global _ATTACK_SURFACE_MAPPING_CACHE
 
@@ -398,6 +433,7 @@ def _process_finding_micro_batch(
     unique_resources: set,
     scan_resource_cache: set,
     mute_rules_cache: dict,
+    scan_categories_cache: dict[tuple[str, str], dict[str, int]],
 ) -> None:
     """
     Process a micro-batch of findings and persist them using bulk operations.
@@ -418,6 +454,7 @@ def _process_finding_micro_batch(
         unique_resources: Set tracking (uid, region) pairs seen in the scan.
         scan_resource_cache: Set of tuples used to create `ResourceScanSummary` rows.
         mute_rules_cache: Map of finding UID -> mute reason gathered before the scan.
+        scan_categories_cache: Dict tracking category counts {(category, severity): {"total", "failed", "new_failed"}}.
     """
     # Accumulate objects for bulk operations
     findings_to_create = []
@@ -573,11 +610,12 @@ def _process_finding_micro_batch(
             resource_failed_findings_cache[resource_uid] += 1
 
         # Create finding object (don't save yet)
+        check_metadata = finding.get_metadata()
         finding_instance = Finding(
             tenant_id=tenant_id,
             uid=finding_uid,
             delta=delta,
-            check_metadata=finding.get_metadata(),
+            check_metadata=check_metadata,
             status=status,
             status_extended=finding.status_extended,
             severity=finding.severity,
@@ -590,6 +628,7 @@ def _process_finding_micro_batch(
             muted_at=datetime.now(tz=timezone.utc) if is_muted else None,
             muted_reason=muted_reason,
             compliance=finding.compliance,
+            categories=check_metadata.get("categories", []) or [],
         )
         findings_to_create.append(finding_instance)
         resource_denormalized_data.append((finding_instance, resource_instance))
@@ -604,6 +643,16 @@ def _process_finding_micro_batch(
             )
         )
 
+        # Track categories with counts for ScanCategorySummary by (category, severity)
+        aggregate_category_counts(
+            categories=check_metadata.get("categories", []) or [],
+            severity=finding.severity.value,
+            status=status.value,
+            delta=delta.value if delta else None,
+            muted=is_muted,
+            cache=scan_categories_cache,
+        )
+
     # Bulk operations within single transaction
     with rls_transaction(tenant_id):
         # Bulk create findings
@@ -703,6 +752,7 @@ def perform_prowler_scan(
     exception = None
     unique_resources = set()
     scan_resource_cache: set[tuple[str, str, str, str]] = set()
+    scan_categories_cache: dict[tuple[str, str], dict[str, int]] = {}
     start_time = time.time()
     exc = None
 
@@ -792,6 +842,7 @@ def perform_prowler_scan(
                     unique_resources=unique_resources,
                     scan_resource_cache=scan_resource_cache,
                     mute_rules_cache=mute_rules_cache,
+                    scan_categories_cache=scan_categories_cache,
                 )
 
             # Update scan progress
@@ -851,13 +902,33 @@ def perform_prowler_scan(
                 resource_scan_summaries, batch_size=500, ignore_conflicts=True
             )
     except Exception as filter_exception:
-        import sentry_sdk
-
         sentry_sdk.capture_exception(filter_exception)
         logger.error(
             f"Error storing filter values for scan {scan_id}: {filter_exception}"
         )
 
+    try:
+        if scan_categories_cache:
+            category_summaries = [
+                ScanCategorySummary(
+                    tenant_id=tenant_id,
+                    scan_id=scan_id,
+                    category=category,
+                    severity=severity,
+                    total_findings=counts["total"],
+                    failed_findings=counts["failed"],
+                    new_failed_findings=counts["new_failed"],
+                )
+                for (category, severity), counts in scan_categories_cache.items()
+            ]
+            with rls_transaction(tenant_id):
+                ScanCategorySummary.objects.bulk_create(
+                    category_summaries, batch_size=500, ignore_conflicts=True
+                )
+    except Exception as cat_exception:
+        sentry_sdk.capture_exception(cat_exception)
+        logger.error(f"Error storing categories for scan {scan_id}: {cat_exception}")
+
     serializer = ScanTaskSerializer(instance=scan_instance)
     return serializer.data
 

api/src/backend/tasks/tasks.py

@@ -12,6 +12,7 @@ from tasks.jobs.backfill import (
     backfill_compliance_summaries,
     backfill_daily_severity_summaries,
     backfill_resource_scan_summaries,
+    backfill_scan_category_summaries,
 )
 from tasks.jobs.connection import (
     check_integration_connection,
@@ -534,6 +535,21 @@ def backfill_daily_severity_summaries_task(tenant_id: str, days: int = None):
     return backfill_daily_severity_summaries(tenant_id=tenant_id, days=days)
 
 
+@shared_task(name="backfill-scan-category-summaries", queue="backfill")
+@handle_provider_deletion
+def backfill_scan_category_summaries_task(tenant_id: str, scan_id: str):
+    """
+    Backfill ScanCategorySummary for a completed scan.
+
+    Aggregates unique categories from findings and creates a summary row.
+
+    Args:
+        tenant_id (str): The tenant identifier.
+        scan_id (str): The scan identifier.
+    """
+    return backfill_scan_category_summaries(tenant_id=tenant_id, scan_id=scan_id)
+
+
 @shared_task(base=RLSTask, name="scan-compliance-overviews", queue="compliance")
 @handle_provider_deletion
 def create_compliance_requirements_task(tenant_id: str, scan_id: str):

api/src/backend/tasks/tests/test_backfill.py

@@ -4,14 +4,19 @@ import pytest
 from tasks.jobs.backfill import (
     backfill_compliance_summaries,
     backfill_resource_scan_summaries,
+    backfill_scan_category_summaries,
 )
 
 from api.models import (
     ComplianceOverviewSummary,
+    Finding,
     ResourceScanSummary,
     Scan,
+    ScanCategorySummary,
     StateChoices,
 )
+from prowler.lib.check.models import Severity
+from prowler.lib.outputs.finding import Status
 
 
 @pytest.fixture(scope="function")
@@ -46,6 +51,45 @@ def get_not_completed_scans(providers_fixture):
     return scan_1, scan_2
 
 
+@pytest.fixture(scope="function")
+def findings_with_categories_fixture(scans_fixture, resources_fixture):
+    scan = scans_fixture[0]
+    resource = resources_fixture[0]
+
+    finding = Finding.objects.create(
+        tenant_id=scan.tenant_id,
+        uid="finding_with_categories",
+        scan=scan,
+        delta="new",
+        status=Status.FAIL,
+        status_extended="test status",
+        impact=Severity.critical,
+        impact_extended="test impact",
+        severity=Severity.critical,
+        raw_result={"status": Status.FAIL},
+        check_id="test_check",
+        check_metadata={"CheckId": "test_check"},
+        categories=["gen-ai", "security"],
+        first_seen_at="2024-01-02T00:00:00Z",
+    )
+    finding.add_resources([resource])
+    return finding
+
+
+@pytest.fixture(scope="function")
+def scan_category_summary_fixture(scans_fixture):
+    scan = scans_fixture[0]
+    return ScanCategorySummary.objects.create(
+        tenant_id=scan.tenant_id,
+        scan=scan,
+        category="existing-category",
+        severity=Severity.critical,
+        total_findings=1,
+        failed_findings=0,
+        new_failed_findings=0,
+    )
+
+
 @pytest.mark.django_db
 class TestBackfillResourceScanSummaries:
     def test_already_backfilled(self, resource_scan_summary_data):
@@ -172,3 +216,47 @@ class TestBackfillComplianceSummaries:
             assert summary.requirements_failed == expected_counts["requirements_failed"]
             assert summary.requirements_manual == expected_counts["requirements_manual"]
             assert summary.total_requirements == expected_counts["total_requirements"]
+
+
+@pytest.mark.django_db
+class TestBackfillScanCategorySummaries:
+    def test_already_backfilled(self, scan_category_summary_fixture):
+        tenant_id = scan_category_summary_fixture.tenant_id
+        scan_id = scan_category_summary_fixture.scan_id
+
+        result = backfill_scan_category_summaries(str(tenant_id), str(scan_id))
+
+        assert result == {"status": "already backfilled"}
+
+    def test_not_completed_scan(self, get_not_completed_scans):
+        for scan in get_not_completed_scans:
+            result = backfill_scan_category_summaries(str(scan.tenant_id), str(scan.id))
+            assert result == {"status": "scan is not completed"}
+
+    def test_no_categories_to_backfill(self, scans_fixture):
+        scan = scans_fixture[1]  # Failed scan with no findings
+        result = backfill_scan_category_summaries(str(scan.tenant_id), str(scan.id))
+        assert result == {"status": "no categories to backfill"}
+
+    def test_successful_backfill(self, findings_with_categories_fixture):
+        finding = findings_with_categories_fixture
+        tenant_id = str(finding.tenant_id)
+        scan_id = str(finding.scan_id)
+
+        result = backfill_scan_category_summaries(tenant_id, scan_id)
+
+        # 2 categories × 1 severity = 2 rows
+        assert result == {"status": "backfilled", "categories_count": 2}
+
+        summaries = ScanCategorySummary.objects.filter(
+            tenant_id=tenant_id, scan_id=scan_id
+        )
+        assert summaries.count() == 2
+        categories = set(summaries.values_list("category", flat=True))
+        assert categories == {"gen-ai", "security"}
+
+        for summary in summaries:
+            assert summary.severity == Severity.critical
+            assert summary.total_findings == 1
+            assert summary.failed_findings == 1
+            assert summary.new_failed_findings == 1

api/src/backend/tasks/tests/test_beat.py

@@ -28,7 +28,7 @@ class TestScheduleProviderScan:
                     "tenant_id": str(provider_instance.tenant_id),
                     "provider_id": str(provider_instance.id),
                 },
-                countdown=1,
+                countdown=5,
             )
 
             task_name = f"scan-perform-scheduled-{provider_instance.id}"

api/src/backend/tasks/tests/test_scan.py

@@ -20,6 +20,7 @@ from tasks.jobs.scan import (
     _process_finding_micro_batch,
     _store_resources,
     aggregate_attack_surface,
+    aggregate_category_counts,
     aggregate_findings,
     create_compliance_requirements,
     perform_prowler_scan,
@@ -1377,6 +1378,7 @@ class TestProcessFindingMicroBatch:
         unique_resources: set[tuple[str, str]] = set()
         scan_resource_cache: set[tuple[str, str, str, str]] = set()
         mute_rules_cache = {}
+        scan_categories_cache: dict[tuple[str, str], dict[str, int]] = {}
 
         with (
             patch("tasks.jobs.scan.rls_transaction", new=noop_rls_transaction),
@@ -1394,6 +1396,7 @@ class TestProcessFindingMicroBatch:
                 unique_resources,
                 scan_resource_cache,
                 mute_rules_cache,
+                scan_categories_cache,
             )
 
         created_finding = Finding.objects.get(uid=finding.uid)
@@ -1486,6 +1489,7 @@ class TestProcessFindingMicroBatch:
         unique_resources: set[tuple[str, str]] = set()
         scan_resource_cache: set[tuple[str, str, str, str]] = set()
         mute_rules_cache = {finding.uid: "Muted via rule"}
+        scan_categories_cache: dict[tuple[str, str], dict[str, int]] = {}
 
         with (
             patch("tasks.jobs.scan.rls_transaction", new=noop_rls_transaction),
@@ -1503,6 +1507,7 @@ class TestProcessFindingMicroBatch:
                 unique_resources,
                 scan_resource_cache,
                 mute_rules_cache,
+                scan_categories_cache,
             )
 
         existing_resource.refresh_from_db()
@@ -1610,6 +1615,7 @@ class TestProcessFindingMicroBatch:
         unique_resources: set[tuple[str, str]] = set()
         scan_resource_cache: set[tuple[str, str, str, str]] = set()
         mute_rules_cache = {}
+        scan_categories_cache: dict[tuple[str, str], dict[str, int]] = {}
 
         with (
             patch("tasks.jobs.scan.rls_transaction", new=noop_rls_transaction),
@@ -1628,6 +1634,7 @@ class TestProcessFindingMicroBatch:
                 unique_resources,
                 scan_resource_cache,
                 mute_rules_cache,
+                scan_categories_cache,
             )
 
         # Verify the long UID finding was NOT created
@@ -1648,6 +1655,118 @@ class TestProcessFindingMicroBatch:
             for call in warning_calls
         )
 
+    def test_process_finding_micro_batch_tracks_categories(
+        self, tenants_fixture, scans_fixture
+    ):
+        tenant = tenants_fixture[0]
+        scan = scans_fixture[0]
+        provider = scan.provider
+
+        finding1 = FakeFinding(
+            uid="finding-cat-1",
+            status=StatusChoices.PASS,
+            status_extended="all good",
+            severity=Severity.low,
+            check_id="genai_check",
+            resource_uid="arn:aws:bedrock:::model/test",
+            resource_name="test-model",
+            region="us-east-1",
+            service_name="bedrock",
+            resource_type="model",
+            resource_tags={},
+            resource_metadata={},
+            resource_details={},
+            partition="aws",
+            raw={},
+            compliance={},
+            metadata={"categories": ["gen-ai", "security"]},
+            muted=False,
+        )
+
+        finding2 = FakeFinding(
+            uid="finding-cat-2",
+            status=StatusChoices.FAIL,
+            status_extended="bad",
+            severity=Severity.high,
+            check_id="iam_check",
+            resource_uid="arn:aws:iam:::user/test",
+            resource_name="test-user",
+            region="us-east-1",
+            service_name="iam",
+            resource_type="user",
+            resource_tags={},
+            resource_metadata={},
+            resource_details={},
+            partition="aws",
+            raw={},
+            compliance={},
+            metadata={"categories": ["security", "iam"]},
+            muted=False,
+        )
+
+        resource_cache = {}
+        tag_cache = {}
+        last_status_cache = {}
+        resource_failed_findings_cache = {}
+        unique_resources: set[tuple[str, str]] = set()
+        scan_resource_cache: set[tuple[str, str, str, str]] = set()
+        mute_rules_cache = {}
+        scan_categories_cache: dict[tuple[str, str], dict[str, int]] = {}
+
+        with (
+            patch("tasks.jobs.scan.rls_transaction", new=noop_rls_transaction),
+            patch("api.db_utils.rls_transaction", new=noop_rls_transaction),
+        ):
+            _process_finding_micro_batch(
+                str(tenant.id),
+                [finding1, finding2],
+                scan,
+                provider,
+                resource_cache,
+                tag_cache,
+                last_status_cache,
+                resource_failed_findings_cache,
+                unique_resources,
+                scan_resource_cache,
+                mute_rules_cache,
+                scan_categories_cache,
+            )
+
+        # finding1: PASS, severity=low, categories=["gen-ai", "security"]
+        # finding2: FAIL, severity=high, categories=["security", "iam"]
+        # Keys are (category, severity) tuples
+        assert set(scan_categories_cache.keys()) == {
+            ("gen-ai", "low"),
+            ("security", "low"),
+            ("security", "high"),
+            ("iam", "high"),
+        }
+        assert scan_categories_cache[("gen-ai", "low")] == {
+            "total": 1,
+            "failed": 0,
+            "new_failed": 0,
+        }
+        assert scan_categories_cache[("security", "low")] == {
+            "total": 1,
+            "failed": 0,
+            "new_failed": 0,
+        }
+        assert scan_categories_cache[("security", "high")] == {
+            "total": 1,
+            "failed": 1,
+            "new_failed": 1,
+        }
+        assert scan_categories_cache[("iam", "high")] == {
+            "total": 1,
+            "failed": 1,
+            "new_failed": 1,
+        }
+
+        created_finding1 = Finding.objects.get(uid="finding-cat-1")
+        created_finding2 = Finding.objects.get(uid="finding-cat-2")
+        assert set(created_finding1.categories) == {"gen-ai", "security"}
+        assert set(created_finding2.categories) == {"security", "iam"}
+
 
 @pytest.mark.django_db
 class TestCreateComplianceRequirements:
@@ -3756,3 +3875,150 @@ class TestAggregateAttackSurface:
             aggregate_attack_surface(str(tenant.id), str(scan.id))
 
         mock_select_related.assert_called_once_with("provider")
+
+
+class TestAggregateCategoryCounts:
+    """Test aggregate_category_counts helper function."""
+
+    def test_aggregate_category_counts_basic(self):
+        """Test basic category counting for a non-muted PASS finding."""
+        cache: dict[tuple[str, str], dict[str, int]] = {}
+        aggregate_category_counts(
+            categories=["security", "iam"],
+            severity="high",
+            status="PASS",
+            delta=None,
+            muted=False,
+            cache=cache,
+        )
+
+        assert ("security", "high") in cache
+        assert ("iam", "high") in cache
+        assert cache[("security", "high")] == {"total": 1, "failed": 0, "new_failed": 0}
+        assert cache[("iam", "high")] == {"total": 1, "failed": 0, "new_failed": 0}
+
+    def test_aggregate_category_counts_fail_not_muted(self):
+        """Test category counting for a non-muted FAIL finding."""
+        cache: dict[tuple[str, str], dict[str, int]] = {}
+        aggregate_category_counts(
+            categories=["security"],
+            severity="critical",
+            status="FAIL",
+            delta=None,
+            muted=False,
+            cache=cache,
+        )
+
+        assert cache[("security", "critical")] == {
+            "total": 1,
+            "failed": 1,
+            "new_failed": 0,
+        }
+
+    def test_aggregate_category_counts_new_fail(self):
+        """Test category counting for a new FAIL finding (delta='new')."""
+        cache: dict[tuple[str, str], dict[str, int]] = {}
+        aggregate_category_counts(
+            categories=["gen-ai"],
+            severity="high",
+            status="FAIL",
+            delta="new",
+            muted=False,
+            cache=cache,
+        )
+
+        assert cache[("gen-ai", "high")] == {"total": 1, "failed": 1, "new_failed": 1}
+
+    def test_aggregate_category_counts_muted_finding(self):
+        """Test that muted findings are excluded from all counts."""
+        cache: dict[tuple[str, str], dict[str, int]] = {}
+        aggregate_category_counts(
+            categories=["security"],
+            severity="high",
+            status="FAIL",
+            delta="new",
+            muted=True,
+            cache=cache,
+        )
+
+        assert cache[("security", "high")] == {"total": 0, "failed": 0, "new_failed": 0}
+
+    def test_aggregate_category_counts_accumulates(self):
+        """Test that multiple calls accumulate counts."""
+        cache: dict[tuple[str, str], dict[str, int]] = {}
+
+        # First finding: PASS
+        aggregate_category_counts(
+            categories=["security"],
+            severity="high",
+            status="PASS",
+            delta=None,
+            muted=False,
+            cache=cache,
+        )
+
+        # Second finding: FAIL (new)
+        aggregate_category_counts(
+            categories=["security"],
+            severity="high",
+            status="FAIL",
+            delta="new",
+            muted=False,
+            cache=cache,
+        )
+
+        # Third finding: FAIL (changed)
+        aggregate_category_counts(
+            categories=["security"],
+            severity="high",
+            status="FAIL",
+            delta="changed",
+            muted=False,
+            cache=cache,
+        )
+
+        assert cache[("security", "high")] == {"total": 3, "failed": 2, "new_failed": 1}
+
+    def test_aggregate_category_counts_empty_categories(self):
+        """Test with empty categories list."""
+        cache: dict[tuple[str, str], dict[str, int]] = {}
+        aggregate_category_counts(
+            categories=[],
+            severity="high",
+            status="FAIL",
+            delta="new",
+            muted=False,
+            cache=cache,
+        )
+
+        assert cache == {}
+
+    def test_aggregate_category_counts_changed_delta(self):
+        """Test that changed delta increments failed but not new_failed."""
+        cache: dict[tuple[str, str], dict[str, int]] = {}
+        aggregate_category_counts(
+            categories=["iam"],
+            severity="medium",
+            status="FAIL",
+            delta="changed",
+            muted=False,
+            cache=cache,
+        )
+
+        assert cache[("iam", "medium")] == {"total": 1, "failed": 1, "new_failed": 0}
+
+    def test_aggregate_category_counts_multiple_categories_single_finding(self):
+        """Test single finding with multiple categories."""
+        cache: dict[tuple[str, str], dict[str, int]] = {}
+        aggregate_category_counts(
+            categories=["security", "compliance", "data-protection"],
+            severity="low",
+            status="FAIL",
+            delta="new",
+            muted=False,
+            cache=cache,
+        )
+
+        assert len(cache) == 3
+        for cat in ["security", "compliance", "data-protection"]:
+            assert cache[(cat, "low")] == {"total": 1, "failed": 1, "new_failed": 1}

dashboard/compliance/prowler_threatscore_alibabacloud.py

@@ -0,0 +1,28 @@
+import warnings
+
+from dashboard.common_methods import get_section_containers_threatscore
+
+warnings.filterwarnings("ignore")
+
+
+def get_table(data):
+    aux = data[
+        [
+            "REQUIREMENTS_ID",
+            "REQUIREMENTS_DESCRIPTION",
+            "REQUIREMENTS_ATTRIBUTES_SECTION",
+            "REQUIREMENTS_ATTRIBUTES_SUBSECTION",
+            "CHECKID",
+            "STATUS",
+            "REGION",
+            "ACCOUNTID",
+            "RESOURCEID",
+        ]
+    ].copy()
+
+    return get_section_containers_threatscore(
+        aux,
+        "REQUIREMENTS_ATTRIBUTES_SECTION",
+        "REQUIREMENTS_ATTRIBUTES_SUBSECTION",
+        "REQUIREMENTS_ID",
+    )

dashboard/pages/compliance.py

@@ -407,9 +407,11 @@ def display_data(
             compliance_module = importlib.import_module(
                 f"dashboard.compliance.{current}"
             )
-            data = data.drop_duplicates(
-                subset=["CHECKID", "STATUS", "MUTED", "RESOURCEID", "STATUSEXTENDED"]
-            )
+            # Build subset list based on available columns
+            dedup_columns = ["CHECKID", "STATUS", "RESOURCEID", "STATUSEXTENDED"]
+            if "MUTED" in data.columns:
+                dedup_columns.insert(2, "MUTED")
+            data = data.drop_duplicates(subset=dedup_columns)
 
             if "threatscore" in analytics_input:
                 data = get_threatscore_mean_by_pillar(data)
@@ -652,6 +654,7 @@ def get_table(current_compliance, table):
 def get_threatscore_mean_by_pillar(df):
     score_per_pillar = {}
     max_score_per_pillar = {}
+    counted_findings_per_pillar = {}
 
     for _, row in df.iterrows():
         pillar = (
@@ -663,6 +666,18 @@ def get_threatscore_mean_by_pillar(df):
         if pillar not in score_per_pillar:
             score_per_pillar[pillar] = 0
             max_score_per_pillar[pillar] = 0
+            counted_findings_per_pillar[pillar] = set()
+
+        # Skip muted findings for score calculation
+        is_muted = "MUTED" in df.columns and row.get("MUTED") == "True"
+        if is_muted:
+            continue
+
+        # Create unique finding identifier to avoid counting duplicates
+        finding_id = f"{row.get('CHECKID', '')}_{row.get('RESOURCEID', '')}"
+        if finding_id in counted_findings_per_pillar[pillar]:
+            continue
+        counted_findings_per_pillar[pillar].add(finding_id)
 
         level_of_risk = pd.to_numeric(
             row["REQUIREMENTS_ATTRIBUTES_LEVELOFRISK"], errors="coerce"
@@ -706,6 +721,10 @@ def get_table_prowler_threatscore(df):
     score_per_pillar = {}
     max_score_per_pillar = {}
     pillars = {}
+    counted_findings_per_pillar = {}
+    counted_pass = set()
+    counted_fail = set()
+    counted_muted = set()
 
     df_copy = df.copy()
 
@@ -720,6 +739,24 @@ def get_table_prowler_threatscore(df):
             pillars[pillar] = {"FAIL": 0, "PASS": 0, "MUTED": 0}
             score_per_pillar[pillar] = 0
             max_score_per_pillar[pillar] = 0
+            counted_findings_per_pillar[pillar] = set()
+
+        # Create unique finding identifier
+        finding_id = f"{row.get('CHECKID', '')}_{row.get('RESOURCEID', '')}"
+
+        # Check if muted
+        is_muted = "MUTED" in df_copy.columns and row.get("MUTED") == "True"
+
+        # Count muted findings (separate from score calculation)
+        if is_muted and finding_id not in counted_muted:
+            counted_muted.add(finding_id)
+            pillars[pillar]["MUTED"] += 1
+            continue  # Skip muted findings for score calculation
+
+        # Skip if already counted for this pillar
+        if finding_id in counted_findings_per_pillar[pillar]:
+            continue
+        counted_findings_per_pillar[pillar].add(finding_id)
 
         level_of_risk = pd.to_numeric(
             row["REQUIREMENTS_ATTRIBUTES_LEVELOFRISK"], errors="coerce"
@@ -738,13 +775,14 @@ def get_table_prowler_threatscore(df):
         max_score_per_pillar[pillar] += level_of_risk * weight
 
         if row["STATUS"] == "PASS":
-            pillars[pillar]["PASS"] += 1
+            if finding_id not in counted_pass:
+                counted_pass.add(finding_id)
+                pillars[pillar]["PASS"] += 1
             score_per_pillar[pillar] += level_of_risk * weight
         elif row["STATUS"] == "FAIL":
-            pillars[pillar]["FAIL"] += 1
-
-        if "MUTED" in row and row["MUTED"] == "True":
-            pillars[pillar]["MUTED"] += 1
+            if finding_id not in counted_fail:
+                counted_fail.add(finding_id)
+                pillars[pillar]["FAIL"] += 1
 
     result_df = []
 

docker-compose-dev.yml

@@ -41,6 +41,9 @@ services:
     volumes:
       - "./ui:/app"
       - "/app/node_modules"
+    depends_on:
+      mcp-server:
+        condition: service_healthy
 
   postgres:
     image: postgres:16.3-alpine3.20
@@ -57,7 +60,11 @@ services:
     ports:
       - "${POSTGRES_PORT:-5432}:${POSTGRES_PORT:-5432}"
     healthcheck:
-      test: ["CMD-SHELL", "sh -c 'pg_isready -U ${POSTGRES_ADMIN_USER} -d ${POSTGRES_DB}'"]
+      test:
+        [
+          "CMD-SHELL",
+          "sh -c 'pg_isready -U ${POSTGRES_ADMIN_USER} -d ${POSTGRES_DB}'",
+        ]
       interval: 5s
       timeout: 5s
       retries: 5
@@ -118,6 +125,32 @@ services:
       - "../docker-entrypoint.sh"
       - "beat"
 
+  mcp-server:
+    build:
+      context: ./mcp_server
+      dockerfile: Dockerfile
+    environment:
+      - PROWLER_MCP_TRANSPORT_MODE=http
+    env_file:
+      - path: .env
+        required: false
+    ports:
+      - "8000:8000"
+    volumes:
+      - ./mcp_server/prowler_mcp_server:/app/prowler_mcp_server
+      - ./mcp_server/pyproject.toml:/app/pyproject.toml
+      - ./mcp_server/entrypoint.sh:/app/entrypoint.sh
+    command: ["uvicorn", "--host", "0.0.0.0", "--port", "8000"]
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          "wget -q -O /dev/null http://127.0.0.1:8000/health || exit 1",
+        ]
+      interval: 10s
+      timeout: 5s
+      retries: 3
+
 volumes:
   outputs:
     driver: local

docker-compose.yml

@@ -1,3 +1,9 @@
+# Production Docker Compose configuration
+# Uses pre-built images from Docker Hub (prowlercloud/*)
+#
+# For development with local builds and hot-reload, use docker-compose-dev.yml instead:
+#   docker compose -f docker-compose-dev.yml up
+#
 services:
   api:
     hostname: "prowler-api"
@@ -26,6 +32,9 @@ services:
         required: false
     ports:
       - ${UI_PORT:-3000}:${UI_PORT:-3000}
+    depends_on:
+      mcp-server:
+        condition: service_healthy
 
   postgres:
     image: postgres:16.3-alpine3.20
@@ -93,6 +102,22 @@ services:
       - "../docker-entrypoint.sh"
       - "beat"
 
+  mcp-server:
+    image: prowlercloud/prowler-mcp:${PROWLER_MCP_VERSION:-stable}
+    environment:
+      - PROWLER_MCP_TRANSPORT_MODE=http
+    env_file:
+      - path: .env
+        required: false
+    ports:
+      - "8000:8000"
+    command: ["uvicorn", "--host", "0.0.0.0", "--port", "8000"]
+    healthcheck:
+      test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:8000/health || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 3
+
 volumes:
   output:
     driver: local

docs/developer-guide/check-metadata-guidelines.mdx

@@ -213,3 +213,5 @@ Also is important to keep all code examples as short as possible, including the
 | software-supply-chain   | Detects or prevents tampering, unauthorized packages, or third-party risks in software supply chain                                                                                               |
 | e3                      | M365-specific controls enabled by or dependent on an E3 license (e.g., baseline security policies, conditional access)                                                                            |
 | e5                      | M365-specific controls enabled by or dependent on an E5 license (e.g., advanced threat protection, audit, DLP, and eDiscovery)                                                                    |
+| privilege-escalation    | Detects IAM policies or permissions that allow identities to elevate their privileges beyond their intended scope, potentially gaining administrator or higher-level access through specific action combinations |
+| ec2-imdsv1              | Identifies EC2 instances using Instance Metadata Service version 1 (IMDSv1), which is vulnerable to SSRF attacks and should be replaced with IMDSv2 for enhanced security                        |

docs/developer-guide/mcp-server.mdx

@@ -0,0 +1,447 @@
+---
+title: 'Extending the MCP Server'
+---
+
+This guide explains how to extend the Prowler MCP Server with new tools and features.
+
+<Info>
+**New to Prowler MCP Server?** Start with the user documentation:
+- [Overview](/getting-started/products/prowler-mcp) - Key capabilities, use cases, and deployment options
+- [Installation](/getting-started/installation/prowler-mcp) - Install locally or use the managed server
+- [Configuration](/getting-started/basic-usage/prowler-mcp) - Configure Claude Desktop, Cursor, and other MCP hosts
+- [Tools Reference](/getting-started/basic-usage/prowler-mcp-tools) - Complete list of all available tools
+</Info>
+
+## Introduction
+
+The Prowler MCP Server brings the entire Prowler ecosystem to AI assistants through the [Model Context Protocol (MCP)](https://modelcontextprotocol.io). It enables seamless integration with AI tools like Claude Desktop, Cursor, and other MCP clients.
+
+The server follows a modular architecture with three independent sub-servers:
+
+| Sub-Server | Auth Required | Description |
+|------------|---------------|-------------|
+| Prowler App | Yes | Full access to Prowler Cloud and Self-Managed features |
+| Prowler Hub | No | Security checks catalog with **over 1000 checks**, fixers, and **70+ compliance frameworks** |
+| Prowler Documentation | No | Full-text search and retrieval of official documentation |
+
+<Note>
+For a complete list of tools and their descriptions, see the [Tools Reference](/getting-started/basic-usage/prowler-mcp-tools).
+</Note>
+
+## Architecture Overview
+
+The MCP Server architecture is illustrated in the [Overview documentation](/getting-started/products/prowler-mcp#mcp-server-architecture). AI assistants connect through the MCP protocol to access Prowler's three main components.
+
+### Server Structure
+
+The main server orchestrates three sub-servers with prefixed namespacing:
+
+```
+mcp_server/prowler_mcp_server/
+├── server.py                 # Main orchestrator
+├── main.py                   # CLI entry point
+├── prowler_hub/
+├── prowler_app/
+│   ├── tools/                # Tool implementations
+│   ├── models/               # Pydantic models
+│   └── utils/                # API client, auth, loader
+└── prowler_documentation/
+```
+
+### Tool Registration Patterns
+
+The MCP Server uses two patterns for tool registration:
+
+1. **Direct Decorators** (Prowler Hub/Docs): Tools are registered using `@mcp.tool()` decorators
+2. **Auto-Discovery** (Prowler App): All public methods of `BaseTool` subclasses are auto-registered
+
+## Adding Tools to Prowler App
+
+### Step 1: Create the Tool Class
+
+Create a new file or add to an existing file in `prowler_app/tools/`:
+
+```python
+# prowler_app/tools/new_feature.py
+from typing import Any
+
+from pydantic import Field
+
+from prowler_mcp_server.prowler_app.models.new_feature import (
+    FeatureListResponse,
+    DetailedFeature,
+)
+from prowler_mcp_server.prowler_app.tools.base import BaseTool
+
+
+class NewFeatureTools(BaseTool):
+    """Tools for managing new features."""
+
+    async def list_features(
+        self,
+        status: str | None = Field(
+            default=None,
+            description="Filter by status (active, inactive, pending)"
+        ),
+        page_size: int = Field(
+            default=50,
+            description="Number of results per page (1-100)"
+        ),
+    ) -> dict[str, Any]:
+        """List all features with optional filtering.
+
+        Returns a lightweight list of features optimized for LLM consumption.
+        Use get_feature for complete information about a specific feature.
+        """
+        # Validate parameters
+        self.api_client.validate_page_size(page_size)
+
+        # Build query parameters
+        params: dict[str, Any] = {"page[size]": page_size}
+        if status:
+            params["filter[status]"] = status
+
+        # Make API request
+        clean_params = self.api_client.build_filter_params(params)
+        response = await self.api_client.get("/api/v1/features", params=clean_params)
+
+        # Transform to LLM-friendly format
+        return FeatureListResponse.from_api_response(response).model_dump()
+
+    async def get_feature(
+        self,
+        feature_id: str = Field(description="The UUID of the feature"),
+    ) -> dict[str, Any]:
+        """Get detailed information about a specific feature.
+
+        Returns complete feature details including configuration and metadata.
+        """
+        try:
+            response = await self.api_client.get(f"/api/v1/features/{feature_id}")
+            return DetailedFeature.from_api_response(response["data"]).model_dump()
+        except Exception as e:
+            self.logger.error(f"Failed to get feature {feature_id}: {e}")
+            return {"error": str(e), "status": "failed"}
+```
+
+### Step 2: Create the Models
+
+Create corresponding models in `prowler_app/models/`:
+
+```python
+# prowler_app/models/new_feature.py
+from typing import Any
+
+from pydantic import Field
+
+from prowler_mcp_server.prowler_app.models.base import MinimalSerializerMixin
+
+
+class SimplifiedFeature(MinimalSerializerMixin):
+    """Lightweight feature for list operations."""
+
+    id: str = Field(description="Unique feature identifier")
+    name: str = Field(description="Feature name")
+    status: str = Field(description="Current status")
+
+    @classmethod
+    def from_api_response(cls, data: dict[str, Any]) -> "SimplifiedFeature":
+        """Transform API response to simplified format."""
+        attributes = data.get("attributes", {})
+        return cls(
+            id=data["id"],
+            name=attributes["name"],
+            status=attributes["status"],
+        )
+
+
+class DetailedFeature(SimplifiedFeature):
+    """Extended feature with complete details."""
+
+    description: str | None = Field(default=None, description="Feature description")
+    configuration: dict[str, Any] | None = Field(default=None, description="Configuration")
+    created_at: str = Field(description="Creation timestamp")
+    updated_at: str = Field(description="Last update timestamp")
+
+    @classmethod
+    def from_api_response(cls, data: dict[str, Any]) -> "DetailedFeature":
+        """Transform API response to detailed format."""
+        attributes = data.get("attributes", {})
+        return cls(
+            id=data["id"],
+            name=attributes["name"],
+            status=attributes["status"],
+            description=attributes.get("description"),
+            configuration=attributes.get("configuration"),
+            created_at=attributes["created_at"],
+            updated_at=attributes["updated_at"],
+        )
+
+
+class FeatureListResponse(MinimalSerializerMixin):
+    """Response wrapper for feature list operations."""
+
+    count: int = Field(description="Total number of features")
+    features: list[SimplifiedFeature] = Field(description="List of features")
+
+    @classmethod
+    def from_api_response(cls, response: dict[str, Any]) -> "FeatureListResponse":
+        """Transform API response to list format."""
+        data = response.get("data", [])
+        features = [SimplifiedFeature.from_api_response(item) for item in data]
+        return cls(count=len(features), features=features)
+```
+
+### Step 3: Verify Auto-Discovery
+
+No manual registration is needed. The `tool_loader.py` automatically discovers and registers all `BaseTool` subclasses. Verify your tool is loaded by checking the server logs:
+
+```
+INFO - Auto-registered 2 tools from NewFeatureTools
+INFO - Loaded and registered: NewFeatureTools
+```
+
+## Adding Tools to Prowler Hub/Docs
+
+For Prowler Hub or Documentation tools, use the `@mcp.tool()` decorator directly:
+
+```python
+# prowler_hub/server.py
+from fastmcp import FastMCP
+
+hub_mcp_server = FastMCP("prowler-hub")
+
+@hub_mcp_server.tool()
+async def get_new_artifact(
+    artifact_id: str,
+) -> dict:
+    """Fetch a specific artifact from Prowler Hub.
+
+    Args:
+        artifact_id: The unique identifier of the artifact
+
+    Returns:
+        Dictionary containing artifact details
+    """
+    response = prowler_hub_client.get(f"/artifact/{artifact_id}")
+    response.raise_for_status()
+    return response.json()
+```
+
+## Model Design Patterns
+
+### MinimalSerializerMixin
+
+All models should use `MinimalSerializerMixin` to optimize responses for LLM consumption:
+
+```python
+from prowler_mcp_server.prowler_app.models.base import MinimalSerializerMixin
+
+class MyModel(MinimalSerializerMixin):
+    """Model that excludes empty values from serialization."""
+    required_field: str
+    optional_field: str | None = None  # Excluded if None
+    empty_list: list = []              # Excluded if empty
+```
+
+This mixin automatically excludes:
+- `None` values
+- Empty strings
+- Empty lists
+- Empty dictionaries
+
+### Two-Tier Model Pattern
+
+Use two-tier models for efficient responses:
+
+- **Simplified**: Lightweight models for list operations
+- **Detailed**: Extended models for single-item retrieval
+
+```python
+class SimplifiedItem(MinimalSerializerMixin):
+    """Use for list operations - minimal fields."""
+    id: str
+    name: str
+    status: str
+
+class DetailedItem(SimplifiedItem):
+    """Use for get operations - extends simplified with details."""
+    description: str | None = None
+    configuration: dict | None = None
+    created_at: str
+    updated_at: str
+```
+
+### Factory Method Pattern
+
+Always implement `from_api_response()` for API transformation:
+
+```python
+@classmethod
+def from_api_response(cls, data: dict[str, Any]) -> "MyModel":
+    """Transform API response to model.
+
+    This method handles the JSON:API format used by Prowler API,
+    extracting attributes and relationships as needed.
+    """
+    attributes = data.get("attributes", {})
+    return cls(
+        id=data["id"],
+        name=attributes["name"],
+        # ... map other fields
+    )
+```
+
+## API Client Usage
+
+The `ProwlerAPIClient` is a singleton that handles authentication and HTTP requests:
+
+```python
+class MyTools(BaseTool):
+    async def my_tool(self) -> dict:
+        # GET request
+        response = await self.api_client.get("/api/v1/endpoint", params={"key": "value"})
+
+        # POST request
+        response = await self.api_client.post(
+            "/api/v1/endpoint",
+            json_data={"data": {"type": "items", "attributes": {...}}}
+        )
+
+        # PATCH request
+        response = await self.api_client.patch(
+            f"/api/v1/endpoint/{id}",
+            json_data={"data": {"attributes": {...}}}
+        )
+
+        # DELETE request
+        response = await self.api_client.delete(f"/api/v1/endpoint/{id}")
+```
+
+### Helper Methods
+
+The API client provides useful helper methods:
+
+```python
+# Validate page size (1-1000)
+self.api_client.validate_page_size(page_size)
+
+# Normalize date range with max days limit
+date_range = self.api_client.normalize_date_range(date_from, date_to, max_days=2)
+
+# Build filter parameters (handles type conversion)
+clean_params = self.api_client.build_filter_params({
+    "filter[status]": "active",
+    "filter[severity__in]": ["high", "critical"],  # Converts to comma-separated
+    "filter[muted]": True,  # Converts to "true"
+})
+
+# Poll async task until completion
+result = await self.api_client.poll_task_until_complete(
+    task_id=task_id,
+    timeout=60,
+    poll_interval=1.0
+)
+```
+
+## Best Practices
+
+### Tool Docstrings
+
+Tool docstrings become description that is going to be read by the LLM. Provide clear usage instructions and common workflows:
+
+```python
+async def search_items(self, status: str = Field(...)) -> dict:
+    """Search items with advanced filtering.
+
+    Returns a lightweight list optimized for LLM consumption.
+    Use get_item for complete details about a specific item.
+
+    Common workflows:
+    - Find critical items: status="critical"
+    - Find recent items: Use date_from parameter
+    """
+```
+
+### Error Handling
+
+Return structured error responses instead of raising exceptions:
+
+```python
+async def get_item(self, item_id: str) -> dict:
+    try:
+        response = await self.api_client.get(f"/api/v1/items/{item_id}")
+        return DetailedItem.from_api_response(response["data"]).model_dump()
+    except Exception as e:
+        self.logger.error(f"Failed to get item {item_id}: {e}")
+        return {"error": str(e), "status": "failed"}
+```
+
+### Parameter Descriptions
+
+Use Pydantic `Field()` with clear descriptions. This also helps LLMs understand
+the purpose of each parameter, so be as descriptive as possible:
+
+```python
+async def list_items(
+    self,
+    severity: list[str] = Field(
+        default=[],
+        description="Filter by severity levels (critical, high, medium, low)"
+    ),
+    status: str | None = Field(
+        default=None,
+        description="Filter by status (PASS, FAIL, MANUAL)"
+    ),
+    page_size: int = Field(
+        default=50,
+        description="Results per page"
+    ),
+) -> dict:
+```
+
+## Development Commands
+
+```bash
+# Navigate to MCP server directory
+cd mcp_server
+
+# Run in STDIO mode (default)
+uv run prowler-mcp
+
+# Run in HTTP mode
+uv run prowler-mcp --transport http --host 0.0.0.0 --port 8000
+
+# Run with environment variables
+PROWLER_APP_API_KEY="pk_xxx" uv run prowler-mcp
+```
+
+For complete installation and deployment options, see:
+- [Installation Guide](/getting-started/installation/prowler-mcp#from-source-development) - Development setup instructions
+- [Configuration Guide](/getting-started/basic-usage/prowler-mcp) - MCP client configuration
+
+For development I recommend to use the [Model Context Protocol Inspector](https://github.com/modelcontextprotocol/inspector) as MCP client to test and debug your tools.
+
+## Related Documentation
+
+<CardGroup cols={2}>
+  <Card title="MCP Server Overview" icon="circle-info" href="/getting-started/products/prowler-mcp">
+    Key capabilities, use cases, and deployment options
+  </Card>
+  <Card title="Tools Reference" icon="wrench" href="/getting-started/basic-usage/prowler-mcp-tools">
+    Complete reference of all available tools
+  </Card>
+  <Card title="Prowler Hub" icon="database" href="/getting-started/products/prowler-hub">
+    Security checks and compliance frameworks catalog
+  </Card>
+  <Card title="Lighthouse AI" icon="robot" href="/getting-started/products/prowler-lighthouse-ai">
+    AI-powered security analyst
+  </Card>
+</CardGroup>
+
+## Additional Resources
+
+- [MCP Protocol Specification](https://modelcontextprotocol.io) - Model Context Protocol details
+- [Prowler API Documentation](https://api.prowler.com/api/v1/docs) - API reference
+- [Prowler Hub API](https://hub.prowler.com/api/docs) - Hub API reference
+- [GitHub Repository](https://github.com/prowler-cloud/prowler) - Source code

docs/docs.json

@@ -19,9 +19,7 @@
         "groups": [
           {
             "group": "Welcome",
-            "pages": [
-              "introduction"
-            ]
+            "pages": ["introduction"]
           },
           {
             "group": "Prowler Cloud",
@@ -51,9 +49,7 @@
           },
           {
             "group": "Prowler Lighthouse AI",
-            "pages": [
-              "getting-started/products/prowler-lighthouse-ai"
-            ]
+            "pages": ["getting-started/products/prowler-lighthouse-ai"]
           },
           {
             "group": "Prowler MCP Server",
@@ -153,9 +149,7 @@
               "user-guide/cli/tutorials/quick-inventory",
               {
                 "group": "Tutorials",
-                "pages": [
-                  "user-guide/cli/tutorials/parallel-execution"
-                ]
+                "pages": ["user-guide/cli/tutorials/parallel-execution"]
               }
             ]
           },
@@ -243,9 +237,7 @@
               },
               {
                 "group": "LLM",
-                "pages": [
-                  "user-guide/providers/llm/getting-started-llm"
-                ]
+                "pages": ["user-guide/providers/llm/getting-started-llm"]
               },
               {
                 "group": "Oracle Cloud Infrastructure",
@@ -258,9 +250,7 @@
           },
           {
             "group": "Compliance",
-            "pages": [
-              "user-guide/compliance/tutorials/threatscore"
-            ]
+            "pages": ["user-guide/compliance/tutorials/threatscore"]
           }
         ]
       },
@@ -277,7 +267,8 @@
               "developer-guide/outputs",
               "developer-guide/integrations",
               "developer-guide/security-compliance-framework",
-              "developer-guide/lighthouse"
+              "developer-guide/lighthouse",
+              "developer-guide/mcp-server"
             ]
           },
           {
@@ -313,21 +304,15 @@
       },
       {
         "tab": "Security",
-        "pages": [
-          "security"
-        ]
+        "pages": ["security"]
       },
       {
         "tab": "Contact Us",
-        "pages": [
-          "contact"
-        ]
+        "pages": ["contact"]
       },
       {
         "tab": "Troubleshooting",
-        "pages": [
-          "troubleshooting"
-        ]
+        "pages": ["troubleshooting"]
       },
       {
         "tab": "About Us",

docs/getting-started/basic-usage/prowler-mcp-tools.mdx

@@ -10,7 +10,7 @@ Complete reference guide for all tools available in the Prowler MCP Server. Tool
 |----------|------------|------------------------|
 | Prowler Hub | 10 tools | No |
 | Prowler Documentation | 2 tools | No |
-| Prowler Cloud/App | 28 tools | Yes |
+| Prowler Cloud/App | 24 tools | Yes |
 
 ## Tool Naming Convention
 
@@ -20,39 +20,6 @@ All tools follow a consistent naming pattern with prefixes:
 - `prowler_docs_*` - Prowler documentation search and retrieval
 - `prowler_app_*` - Prowler Cloud and App (Self-Managed) management tools
 
-## Prowler Hub Tools
-
-Access Prowler's security check catalog and compliance frameworks. **No authentication required.**
-
-### Check Discovery
-
-- **`prowler_hub_get_checks`** - List security checks with advanced filtering options
-- **`prowler_hub_get_check_filters`** - Return available filter values for checks (providers, services, severities, categories, compliances)
-- **`prowler_hub_search_checks`** - Full-text search across check metadata
-- **`prowler_hub_get_check_raw_metadata`** - Fetch raw check metadata in JSON format
-
-### Check Code
-
-- **`prowler_hub_get_check_code`** - Fetch the Python implementation code for a security check
-- **`prowler_hub_get_check_fixer`** - Fetch the automated fixer code for a check (if available)
-
-### Compliance Frameworks
-
-- **`prowler_hub_get_compliance_frameworks`** - List and filter compliance frameworks
-- **`prowler_hub_search_compliance_frameworks`** - Full-text search across compliance frameworks
-
-### Provider Information
-
-- **`prowler_hub_list_providers`** - List Prowler official providers and their services
-- **`prowler_hub_get_artifacts_count`** - Get total count of checks and frameworks in Prowler Hub
-
-## Prowler Documentation Tools
-
-Search and access official Prowler documentation. **No authentication required.**
-
-- **`prowler_docs_search`** - Search the official Prowler documentation using full-text search
-- **`prowler_docs_get_document`** - Retrieve the full markdown content of a specific documentation file
-
 ## Prowler Cloud/App Tools
 
 Manage Prowler Cloud or Prowler App (Self-Managed) features. **Requires authentication.**
@@ -63,49 +30,97 @@ These tools require a valid API key. See the [Configuration Guide](/getting-star
 
 ### Findings Management
 
-- **`prowler_app_list_findings`** - List security findings with advanced filtering
-- **`prowler_app_get_finding`** - Get detailed information about a specific finding
-- **`prowler_app_get_latest_findings`** - Retrieve latest findings from the most recent scans
-- **`prowler_app_get_findings_metadata`** - Get unique metadata values from filtered findings
-- **`prowler_app_get_latest_findings_metadata`** - Get metadata from latest findings across all providers
+Tools for searching, viewing, and analyzing security findings across all cloud providers.
+
+- **`prowler_app_search_security_findings`** - Search and filter security findings with advanced filtering options (severity, status, provider, region, service, check ID, date range, muted status)
+- **`prowler_app_get_finding_details`** - Get comprehensive details about a specific finding including remediation guidance, check metadata, and resource relationships
+- **`prowler_app_get_findings_overview`** - Get aggregate statistics and trends about security findings as a markdown report
 
 ### Provider Management
 
-- **`prowler_app_list_providers`** - List all providers with filtering options
-- **`prowler_app_create_provider`** - Create a new provider in the current tenant
-- **`prowler_app_get_provider`** - Get detailed information about a specific provider
-- **`prowler_app_update_provider`** - Update provider details (alias, etc.)
-- **`prowler_app_delete_provider`** - Delete a specific provider
-- **`prowler_app_test_provider_connection`** - Test provider connection status
+Tools for managing cloud provider connections in Prowler.
 
-### Provider Secrets Management
-
-- **`prowler_app_list_provider_secrets`** - List all provider secrets with filtering
-- **`prowler_app_add_provider_secret`** - Add or update credentials for a provider
-- **`prowler_app_get_provider_secret`** - Get detailed information about a provider secret
-- **`prowler_app_update_provider_secret`** - Update provider secret details
-- **`prowler_app_delete_provider_secret`** - Delete a provider secret
+- **`prowler_app_search_providers`** - Search and view configured providers with their connection status
+- **`prowler_app_connect_provider`** - Register and connect a provider with credentials for security scanning
+- **`prowler_app_delete_provider`** - Permanently remove a provider from Prowler
 
 ### Scan Management
 
-- **`prowler_app_list_scans`** - List all scans with filtering options
-- **`prowler_app_create_scan`** - Trigger a manual scan for a specific provider
-- **`prowler_app_get_scan`** - Get detailed information about a specific scan
-- **`prowler_app_update_scan`** - Update scan details
-- **`prowler_app_get_scan_compliance_report`** - Download compliance report as CSV
-- **`prowler_app_get_scan_report`** - Download ZIP file containing complete scan report
+Tools for managing and monitoring security scans.
 
-### Schedule Management
+- **`prowler_app_list_scans`** - List and filter security scans across all providers
+- **`prowler_app_get_scan`** - Get comprehensive details about a specific scan (progress, duration, resource counts)
+- **`prowler_app_trigger_scan`** - Trigger a manual security scan for a provider
+- **`prowler_app_schedule_daily_scan`** - Schedule automated daily scans for continuous monitoring
+- **`prowler_app_update_scan`** - Update scan name for better organization
 
-- **`prowler_app_schedules_daily_scan`** - Create a daily scheduled scan for a provider
+### Resources Management
 
-### Processor Management
+Tools for searching, viewing, and analyzing cloud resources discovered by Prowler.
 
-- **`prowler_app_processors_list`** - List all processors with filtering
-- **`prowler_app_processors_create`** - Create a new processor (currently only mute lists supported)
-- **`prowler_app_processors_retrieve`** - Get processor details by ID
-- **`prowler_app_processors_partial_update`** - Update processor configuration
-- **`prowler_app_processors_destroy`** - Delete a processor
+- **`prowler_app_list_resources`** - List and filter cloud resources with advanced filtering options (provider, region, service, resource type, tags)
+- **`prowler_app_get_resource`** - Get comprehensive details about a specific resource including configuration, metadata, and finding relationships
+- **`prowler_app_get_resources_overview`** - Get aggregate statistics about cloud resources as a markdown report
+
+### Muting Management
+
+Tools for managing finding muting, including pattern-based bulk muting (mutelist) and finding-specific mute rules.
+
+#### Mutelist (Pattern-Based Muting)
+
+- **`prowler_app_get_mutelist`** - Retrieve the current mutelist configuration for the tenant
+- **`prowler_app_set_mutelist`** - Create or update the mutelist configuration for pattern-based bulk muting
+- **`prowler_app_delete_mutelist`** - Remove the mutelist configuration from the tenant
+
+#### Mute Rules (Finding-Specific Muting)
+
+- **`prowler_app_list_mute_rules`** - Search and filter mute rules with pagination support
+- **`prowler_app_get_mute_rule`** - Retrieve comprehensive details about a specific mute rule
+- **`prowler_app_create_mute_rule`** - Create a new mute rule to mute specific findings with documentation and audit trail
+- **`prowler_app_update_mute_rule`** - Update a mute rule's name, reason, or enabled status
+- **`prowler_app_delete_mute_rule`** - Delete a mute rule from the system
+
+### Compliance Management
+
+Tools for viewing compliance status and framework details across all cloud providers.
+
+- **`prowler_app_get_compliance_overview`** - Get high-level compliance status across all frameworks for a specific scan or provider, including pass/fail statistics per framework
+- **`prowler_app_get_compliance_framework_state_details`** - Get detailed requirement-level breakdown for a specific compliance framework, including failed requirements and associated finding IDs
+
+## Prowler Hub Tools
+
+Access Prowler's security check catalog and compliance frameworks. **No authentication required.**
+
+Tools follow a **two-tier pattern**: lightweight listing for browsing + detailed retrieval for complete information.
+
+### Check Discovery and Details
+
+- **`prowler_hub_list_checks`** - List security checks with lightweight data (id, title, severity, provider) and advanced filtering options
+- **`prowler_hub_semantic_search_checks`** - Full-text search across check metadata with lightweight results
+- **`prowler_hub_get_check_details`** - Get comprehensive details for a specific check including risk, remediation guidance, and compliance mappings
+
+### Check Code
+
+- **`prowler_hub_get_check_code`** - Fetch the Python implementation code for a security check
+- **`prowler_hub_get_check_fixer`** - Fetch the automated fixer code for a check (if available)
+
+### Compliance Frameworks
+
+- **`prowler_hub_list_compliances`** - List compliance frameworks with lightweight data (id, name, provider) and filtering options
+- **`prowler_hub_semantic_search_compliances`** - Full-text search across compliance frameworks with lightweight results
+- **`prowler_hub_get_compliance_details`** - Get comprehensive compliance details including requirements and mapped checks
+
+### Providers Information
+
+- **`prowler_hub_list_providers`** - List Prowler official providers
+- **`prowler_hub_get_provider_services`** - Get available services for a specific provider
+
+## Prowler Documentation Tools
+
+Search and access official Prowler documentation. **No authentication required.**
+
+- **`prowler_docs_search`** - Search the official Prowler documentation using full-text search with the `term` parameter
+- **`prowler_docs_get_document`** - Retrieve the full markdown content of a specific documentation file using the path from search results
 
 ## Usage Tips
 

docs/getting-started/basic-usage/prowler-mcp.mdx

@@ -139,7 +139,7 @@ STDIO mode is only available when running the MCP server locally.
           "args": ["/absolute/path/to/prowler/mcp_server/"],
           "env": {
             "PROWLER_APP_API_KEY": "<your-api-key-here>",
-            "PROWLER_API_BASE_URL": "https://api.prowler.com"
+            "API_BASE_URL": "https://api.prowler.com/api/v1"
           }
         }
       }
@@ -147,7 +147,7 @@ STDIO mode is only available when running the MCP server locally.
     ```
 
     <Note>
-    Replace `/absolute/path/to/prowler/mcp_server/` with the actual path. The `PROWLER_API_BASE_URL` is optional and defaults to Prowler Cloud API.
+    Replace `/absolute/path/to/prowler/mcp_server/` with the actual path. The `API_BASE_URL` is optional and defaults to Prowler Cloud API.
     </Note>
 
   </Tab>
@@ -167,7 +167,7 @@ STDIO mode is only available when running the MCP server locally.
             "--env",
             "PROWLER_APP_API_KEY=<your-api-key-here>",
             "--env",
-            "PROWLER_API_BASE_URL=https://api.prowler.com",
+            "API_BASE_URL=https://api.prowler.com/api/v1",
             "prowlercloud/prowler-mcp"
           ]
         }
@@ -176,7 +176,7 @@ STDIO mode is only available when running the MCP server locally.
     ```
 
     <Note>
-    The `PROWLER_API_BASE_URL` is optional and defaults to Prowler Cloud API.
+    The `API_BASE_URL` is optional and defaults to Prowler Cloud API.
     </Note>
 
   </Tab>

docs/getting-started/installation/prowler-app.mdx

@@ -115,10 +115,15 @@ To update the environment file:
 Edit the `.env` file and change version values:
 
 ```env
-PROWLER_UI_VERSION="5.9.0"
-PROWLER_API_VERSION="5.9.0"
+PROWLER_UI_VERSION="5.16.0"
+PROWLER_API_VERSION="5.16.0"
 ```
 
+<Note>
+  You can find the latest versions of Prowler App in the [Releases Github section](https://github.com/prowler-cloud/prowler/releases) or in the [Container Versions](#container-versions) section of this documentation.
+</Note>
+
+
 #### Option 2: Using Docker Compose Pull
 
 ```bash

docs/getting-started/installation/prowler-mcp.mdx

@@ -52,7 +52,7 @@ Choose one of the following installation methods:
     ```bash
     docker run --rm -i \
       -e PROWLER_APP_API_KEY="pk_your_api_key" \
-      -e PROWLER_API_BASE_URL="https://api.prowler.com" \
+      -e API_BASE_URL="https://api.prowler.com/api/v1" \
       prowlercloud/prowler-mcp
     ```
 
@@ -181,19 +181,19 @@ Configure the server using environment variables:
 | Variable | Description | Required | Default |
 |----------|-------------|----------|---------|
 | `PROWLER_APP_API_KEY` | Prowler API key | Only for STDIO mode | - |
-| `PROWLER_API_BASE_URL` | Custom Prowler API endpoint | No | `https://api.prowler.com` |
+| `API_BASE_URL` | Custom Prowler API endpoint | No | `https://api.prowler.com/api/v1` |
 | `PROWLER_MCP_TRANSPORT_MODE` | Default transport mode (overwritten by `--transport` argument) | No | `stdio` |
 
 <CodeGroup>
 ```bash macOS/Linux
 export PROWLER_APP_API_KEY="pk_your_api_key_here"
-export PROWLER_API_BASE_URL="https://api.prowler.com"
+export API_BASE_URL="https://api.prowler.com/api/v1"
 export PROWLER_MCP_TRANSPORT_MODE="http"
 ```
 
 ```bash Windows PowerShell
 $env:PROWLER_APP_API_KEY="pk_your_api_key_here"
-$env:PROWLER_API_BASE_URL="https://api.prowler.com"
+$env:API_BASE_URL="https://api.prowler.com/api/v1"
 $env:PROWLER_MCP_TRANSPORT_MODE="http"
 ```
 </CodeGroup>
@@ -208,7 +208,7 @@ For convenience, create a `.env` file in the `mcp_server` directory:
 
 ```bash .env
 PROWLER_APP_API_KEY=pk_your_api_key_here
-PROWLER_API_BASE_URL=https://api.prowler.com
+API_BASE_URL=https://api.prowler.com/api/v1
 PROWLER_MCP_TRANSPORT_MODE=stdio
 ```
 

docs/getting-started/products/prowler-hub.mdx

@@ -6,7 +6,7 @@ title: "Overview"
 
 **Why this matters**: Every engineer has asked, “What does this check actually do?” Prowler Hub answers that question in one place, lets you pin to a specific version, and pulls definitions into your own tools or dashboards.
 
-![](/images/products/prowler-hub.webp)
+![](/images/products/prowler-hub.png)
 
 <Card title="Go to Prowler Hub" href="https://hub.prowler.com" />
 
@@ -14,4 +14,4 @@ Prowler Hub also provides a fully documented public API that you can integrate i
 
 📚 Explore the API docs at: https://hub.prowler.com/api/docs
 
-Whether you’re customizing policies, managing compliance, or enhancing visibility, Prowler Hub is built to support your security operations.
+Whether you’re customizing policies, managing compliance, or enhancing visibility, Prowler Hub is built to support your security operations.

docs/getting-started/products/prowler-mcp.mdx

@@ -19,12 +19,11 @@ The Prowler MCP Server provides three main integration points:
 ### 1. Prowler Cloud and Prowler App (Self-Managed)
 
 Full access to Prowler Cloud platform and self-managed Prowler App for:
-- **Provider Management**: Create, configure, and manage cloud providers (AWS, Azure, GCP, etc.).
-- **Scan Orchestration**: Trigger on-demand scans and schedule recurring security assessments.
-- **Findings Analysis**: Query, filter, and analyze security findings across all your cloud environments.
-- **Compliance Reporting**: Generate compliance reports for various frameworks (CIS, PCI-DSS, HIPAA, etc.).
-- **Secrets Management**: Securely manage provider credentials and connection details.
-- **Processor Configuration**: Set up the [Prowler Mutelist](/user-guide/tutorials/prowler-app-mute-findings) to mute findings.
+- **Findings Analysis**: Query, filter, and analyze security findings across all your cloud environments
+- **Provider Management**: Create, configure, and manage your configured Prowler providers (AWS, Azure, GCP, etc.)
+- **Scan Orchestration**: Trigger on-demand scans and schedule recurring security assessments
+- **Resource Inventory**: Search and view detailed information about your audited resources
+- **Muting Management**: Create and manage muting lists/rules to suppress non-relevant findings
 
 ### 2. Prowler Hub
 
@@ -49,7 +48,10 @@ The following diagram illustrates the Prowler MCP Server architecture and its in
 <img className="block dark:hidden" src="/images/prowler_mcp_schema_light.png" alt="Prowler MCP Server Schema" />
 <img className="hidden dark:block" src="/images/prowler_mcp_schema_dark.png" alt="Prowler MCP Server Schema" />
 
-The architecture shows how AI assistants connect through the MCP protocol to access Prowler's three main components: Prowler Cloud/App for security operations, Prowler Hub for security knowledge, and Prowler Documentation for guidance and reference.
+The architecture shows how AI assistants connect through the MCP protocol to access Prowler's three main components:
+- Prowler Cloud/App for security operations
+- Prowler Hub for security knowledge
+- Prowler Documentation for guidance and reference.
 
 ## Use Cases
 
@@ -57,12 +59,12 @@ The Prowler MCP Server enables powerful workflows through AI assistants:
 
 **Security Operations**
 - "Show me all critical findings from my AWS production accounts"
-- "What is my compliance status for the PCI standards accross all my AWS accounts according to the latest Prowler scan results?"
-- "Register my new AWS account in Prowler and run an scheduled scan every day"
+- "Register my new AWS account in Prowler and run a scheduled scan every day"
+- "List all muted findings and detect what findgings are muted by a not enough good reason in relation to their severity"
 
 **Security Research**
-- "Explain what the S3 bucket public access check does"
-- "Find all checks related to encryption at rest"
+- "Explain what the S3 bucket public access Prowler check does"
+- "Find all Prowler checks related to encryption at rest"
 - "What is the latest version of the CIS that Prowler is covering per provider?"
 
 **Documentation & Learning**

docs/security.mdx

@@ -24,6 +24,80 @@ We enforce [pre-commit](https://github.com/prowler-cloud/prowler/blob/master/.pr
 
 Our container registries are continuously scanned for vulnerabilities, with findings automatically reported to our security team for assessment and remediation. This process evolves alongside our stack as we adopt new languages, frameworks, and technologies, ensuring our security practices remain comprehensive, proactive, and adaptable.
 
+### Static Application Security Testing (SAST)
+
+We employ multiple SAST tools across our codebase to identify security vulnerabilities, code quality issues, and potential bugs during development:
+
+#### CodeQL Analysis
+- **Scope**: UI (JavaScript/TypeScript), API (Python), and SDK (Python)
+- **Frequency**: On every push and pull request, plus daily scheduled scans
+- **Integration**: Results uploaded to GitHub Security tab via SARIF format
+- **Purpose**: Identifies security vulnerabilities, coding errors, and potential exploits in source code
+
+#### Python Security Scanners
+- **Bandit**: Detects common security issues in Python code (SQL injection, hardcoded passwords, etc.)
+  - Configured to ignore test files and report only high-severity issues
+  - Runs on both SDK and API codebases
+- **Pylint**: Static code analysis with security-focused checks
+  - Integrated into pre-commit hooks and CI/CD pipelines
+
+#### Code Quality & Dead Code Detection
+- **Vulture**: Identifies unused code that could indicate incomplete implementations or security gaps
+- **Flake8**: Style guide enforcement with security-relevant checks
+- **Shellcheck**: Security and correctness checks for shell scripts
+
+### Software Composition Analysis (SCA)
+
+We continuously monitor our dependencies for known vulnerabilities and ensure timely updates:
+
+#### Dependency Vulnerability Scanning
+- **Safety**: Scans Python dependencies against known vulnerability databases
+  - Runs on every commit via pre-commit hooks
+  - Integrated into CI/CD for SDK and API
+  - Configured with selective ignores for tracked exceptions
+- **Trivy**: Multi-purpose scanner for containers and dependencies
+  - Scans all container images (UI, API, SDK, MCP Server)
+  - Checks for vulnerabilities in OS packages and application dependencies
+  - Reports findings to GitHub Security tab
+
+#### Automated Dependency Updates
+- **Dependabot**: Automated pull requests for dependency updates
+  - **Python (pip)**: Monthly updates for SDK
+  - **GitHub Actions**: Monthly updates for workflow dependencies
+  - **Docker**: Monthly updates for base images
+  - Temporarily paused for API and UI to maintain stability during active development
+  - **Security-first approach**: Even when paused, Dependabot automatically creates pull requests for security vulnerabilities, ensuring critical security patches are never delayed
+
+### Container Security
+
+All container images are scanned before deployment:
+
+- **Trivy Vulnerability Scanning**:
+  - Scans images for vulnerabilities and misconfigurations
+  - Generates SARIF reports uploaded to GitHub Security tab
+  - Creates PR comments with scan summaries
+  - Configurable to fail builds on critical findings
+  - Reports include CVE counts and remediation guidance
+- **Hadolint**: Dockerfile linting to enforce best practices
+  - Validates Dockerfile syntax and structure
+  - Ensures secure image building practices
+
+### Secrets Detection
+
+We protect against accidental exposure of sensitive credentials:
+
+- **TruffleHog**: Scans entire codebase and Git history for secrets
+  - Runs on every push and pull request
+  - Pre-commit hook prevents committing secrets
+  - Detects high-entropy strings, API keys, tokens, and credentials
+  - Configured to report verified and unknown findings
+
+### Security Monitoring
+
+- **GitHub Security Tab**: Centralized view of all security findings from CodeQL, Trivy, and other SARIF-compatible tools
+- **Artifact Retention**: Security scan reports retained for post-deployment analysis
+- **PR Comments**: Automated security feedback on pull requests for rapid remediation
+
 ## Reporting Vulnerabilities
 
 At Prowler, we consider the security of our open source software and systems a top priority. But no matter how much effort we put into system security, there can still be vulnerabilities present.

docs/user-guide/providers/iac/getting-started-iac.mdx

@@ -5,18 +5,26 @@ import { VersionBadge } from "/snippets/version-badge.mdx"
 
 Prowler's Infrastructure as Code (IaC) provider enables scanning of local or remote infrastructure code for security and compliance issues using [Trivy](https://trivy.dev/). This provider supports a wide range of IaC frameworks, allowing assessment of code before deployment.
 
-## Supported Scanners
+## Supported IaC Formats
 
-The IaC provider leverages [Trivy](https://trivy.dev/latest/docs/scanner/vulnerability/) to support multiple scanners, including:
+Prowler IaC provider scans the following Infrastructure as Code configurations for misconfigurations and secrets:
 
-- Vulnerability
-- Misconfiguration
-- Secret
-- License
+| Configuration Type | File Patterns                                |
+|--------------------|----------------------------------------------|
+| Kubernetes         | `*.yml`, `*.yaml`, `*.json`                  |
+| Docker             | `Dockerfile`, `Containerfile`                |
+| Terraform          | `*.tf`, `*.tf.json`, `*.tfvars`              |
+| Terraform Plan     | `tfplan`, `*.tfplan`, `*.json`               |
+| CloudFormation     | `*.yml`, `*.yaml`, `*.json`                  |
+| Azure ARM Template | `*.json`                                     |
+| Helm               | `*.yml`, `*.yaml`, `*.tpl`, `*.tar.gz`, etc. |
+| YAML               | `*.yaml`, `*.yml`                            |
+| JSON               | `*.json`                                     |
+| Ansible            | `*.yml`, `*.yaml`, `*.json`, `*.ini`, without extension |
 
 ## How It Works
 
-- The IaC provider scans local directories (or specified paths) for supported IaC files, or scans remote repositories.
+- Prowler App leverages [Trivy](https://trivy.dev/docs/latest/guide/coverage/iac/#scanner) to scan local directories (or specified paths) for supported IaC files, or scans remote repositories.
 - No cloud credentials or authentication are required for local scans.
 - For remote repository scans, authentication can be provided via [git URL](https://git-scm.com/docs/git-clone#_git_urls), CLI flags or environment variables.
   - Check the [IaC Authentication](/user-guide/providers/iac/authentication) page for more details.
@@ -27,6 +35,10 @@ The IaC provider leverages [Trivy](https://trivy.dev/latest/docs/scanner/vulnera
 
 <VersionBadge version="5.14.0" />
 
+### Supported Scanners
+
+Scanner selection is not configurable in Prowler App. Default scanners, misconfig and secret, run automatically during each scan.
+
 ### Step 1: Access Prowler Cloud/App
 
 1. Navigate to [Prowler Cloud](https://cloud.prowler.com/) or launch [Prowler App](/user-guide/tutorials/prowler-app)
@@ -63,6 +75,17 @@ The IaC provider leverages [Trivy](https://trivy.dev/latest/docs/scanner/vulnera
 
 <VersionBadge version="5.8.0" />
 
+### Supported Scanners
+
+Prowler CLI supports the following scanners:
+
+- [Vulnerability](https://trivy.dev/docs/latest/guide/scanner/vulnerability/)
+- [Misconfiguration](https://trivy.dev/docs/latest/guide/scanner/misconfiguration/)
+- [Secret](https://trivy.dev/docs/latest/guide/scanner/secret/)
+- [License](https://trivy.dev/docs/latest/guide/scanner/license/)
+
+By default, only misconfiguration and secret scanners run during a scan. To specify which scanners to use, refer to the [Specify Scanners](#specify-scanners) section below.
+
 ### Usage
 
 Use the `iac` argument to run Prowler with the IaC provider. Specify the directory or repository to scan, frameworks to include, and paths to exclude.
@@ -103,7 +126,7 @@ Authentication for private repositories can be provided using one of the followi
 
 #### Specify Scanners
 
-Scan only vulnerability and misconfiguration scanners:
+To run only specific scanners, use the `--scanners` flag. For example, to scan only for vulnerabilities and misconfigurations:
 
 ```sh
 prowler iac --scan-path ./my-iac-directory --scanners vuln misconfig

docs/user-guide/providers/kubernetes/getting-started-k8s.mdx

@@ -47,8 +47,43 @@ If you are adding an **EKS**, **GKE**, **AKS** or external cluster, follow these
     kubectl create token prowler-sa -n prowler-ns --duration=0
     ```
 
-    - **Security Note:** The `--duration=0` option generates a non-expiring token, which may pose a security risk if not managed properly. Users should decide on an appropriate expiration time based on their security policies. If a limited-time token is preferred, set `--duration=<TIME>` (e.g., `--duration=24h`).
-    - **Important:** If the token expires, Prowler Cloud will no longer be able to authenticate with the cluster. In this case, you will need to generate a new token and **remove and re-add the provider in Prowler Cloud** with the updated `kubeconfig`.
+    - **Security Note:** The `--duration=0` option generates a non-expiring token, which may pose a security risk if not managed properly. Choose an appropriate expiration time based on security policies. For a limited-time token, set `--duration=<TIME>` (e.g., `--duration=24h`).
+    <Note>
+    **Important:** If the token expires, Prowler Cloud can no longer authenticate with the cluster. Generate a new token and **remove and re-add the provider in Prowler Cloud** with the updated `kubeconfig`.
+    </Note>
+    <Tip>
+    **Token Expiration Limits**
+
+
+    When the Kubernetes cluster has `--service-account-max-token-expiration` configured, any token requested with a duration exceeding the maximum allowed value (including `--duration=0`) is automatically reduced to the cluster's maximum token expiration time. As an alternative solution, create a legacy Secret manually. Although Kubernetes no longer creates these secrets automatically, manual creation and linking to a ServiceAccount is still supported. These tokens do not expire until the secret or ServiceAccount is deleted.
+
+      **Steps:**
+
+      1. Create a `secret-sa.yaml` file (or any preferred name) with the following content:
+
+         ```yaml
+         apiVersion: v1
+         kind: Secret
+         metadata:
+           name: prowler-token-long-lived
+           namespace: prowler-ns
+           annotations:
+             kubernetes.io/service-account.name: "prowler-sa"
+         type: kubernetes.io/service-account-token
+         ```
+
+      2. Apply the secret:
+
+         ```console
+         kubectl apply -f secret-sa.yaml
+         ```
+
+      3. Retrieve the token (which will be permanent):
+
+         ```console
+         kubectl get secret prowler-token-long-lived -n prowler-ns -o jsonpath='{.data.token}' | base64 --decode
+         ```
+     </Tip>
 
 3. Update your `kubeconfig` to use the ServiceAccount token:
 

docs/user-guide/providers/mongodbatlas/getting-started-mongodbatlas.mdx

@@ -2,18 +2,83 @@
 title: 'Getting Started with MongoDB Atlas'
 ---
 
+import { VersionBadge } from "/snippets/version-badge.mdx"
+
+Prowler supports MongoDB Atlas both from the CLI and from Prowler Cloud. This guide walks you through the requirements, how to connect the provider in the UI, and how to run scans from the command line.
+
+## Prerequisites
+
+Before you begin, make sure you have:
+
+1. A MongoDB Atlas organization with **API Access** enabled.
+2. An **Organization ID** (24-character hex string).
+3. An **API Key pair** (public and private keys) with appropriate permissions:
+   - **Organization Read Only**: Provides read-only access to everything in the organization, including all projects in the organization. This permission is sufficient for most security checks.
+   - **Organization Owner**: Required to audit the [Auditing configuration](https://www.mongodb.com/docs/api/doc/atlas-admin-api-v2/group/endpoint-auditing) for projects. Database auditing tracks database operations and security events, including authentication attempts, data definition language (DDL) changes, user and role modifications, and privilege grants. This configuration is essential for security monitoring, forensics, and compliance. Without **Organization Owner** permission, the `projects_auditing_enabled` check cannot retrieve the audit configuration status.
+4. Prowler App access (cloud or self-hosted) or the Prowler CLI (`pip install prowler`).
+
+For detailed instructions on creating API keys, see the [MongoDB Atlas authentication guide](./authentication.mdx).
+
+<Warning>
+If **Require IP Access List for the Atlas Administration API** is enabled in your organization settings, you **must** add the IP address of the host running Prowler (or the public IP of Prowler Cloud) to the organization IP Access List or Atlas will reject every API call. You can manage this under **Settings → Organization Settings → Security**. See step 7 of the [authentication guide](./authentication.mdx) for detailed instructions, and refer to the [Prowler Cloud public IP list](../../tutorials/prowler-cloud-public-ips) when using Prowler Cloud.
+</Warning>
+
+<CardGroup cols={2}>
+  <Card title="Prowler Cloud" icon="cloud" href="#prowler-cloud">
+    Onboard MongoDB Atlas using Prowler Cloud
+  </Card>
+  <Card title="Prowler CLI" icon="terminal" href="#prowler-cli">
+    Onboard MongoDB Atlas using Prowler CLI
+  </Card>
+</CardGroup>
+
+## Prowler Cloud
+
+<VersionBadge version="5.15.0" />
+
+### Step 1: Add the provider
+
+1. Navigate to **Cloud Providers** and click **Add Cloud Provider**.
+   ![Add provider list](./img/add-provider-list.png)
+2. Select **MongoDB Atlas** from the provider list.
+3. Enter your **Organization ID** (24 hex characters). This value is visible in the Atlas UI under **Organization Settings**.
+   ![Add organization ID](./img/add-org-id.png)
+4. (Optional) Add a friendly alias to identify this organization in dashboards.
+
+### Step 2: Provide API credentials
+
+1. Click **Next** to open the credentials form.
+2. Paste the **Atlas Public Key** and **Atlas Private Key** generated in the Atlas console.
+   ![Add credentials](./img/add-credentials.png)
+
+### Step 3: Test the connection and start scanning
+
+1. Click **Test connection** to ensure Prowler App can reach the Atlas API.
+2. Save the credentials. The provider will appear in the list with its current connection status.
+3. Launch a scan from the provider row or from the **Scans** page.
+   ![Launch scan](./img/launch-scan.png)
+
+---
+
 ## Prowler CLI
 
-### Authentication Methods
+<VersionBadge version="5.12.0" />
 
-#### Command-Line Arguments
+You can also run MongoDB Atlas assessments directly from the CLI. Both command-line flags and environment variables are supported.
 
+### Step 1: Select an authentication method
+
+Choose one of the following authentication methods:
+
+#### Command-line arguments
 
 ```bash
-prowler mongodbatlas --atlas-public-key <public_key> --atlas-private-key <private_key>
+prowler mongodbatlas \
+  --atlas-public-key <public_key> \
+  --atlas-private-key <private_key>
 ```
 
-#### Environment Variables
+#### Environment variables
 
 ```bash
 export ATLAS_PUBLIC_KEY=<public_key>
@@ -21,33 +86,28 @@ export ATLAS_PRIVATE_KEY=<private_key>
 prowler mongodbatlas
 ```
 
+### Step 2: Run the first scan
 
-
-### Scan All Projects and Clusters
-
-After storing API keys, run Prowler with the following command:
-
-```bash
-prowler mongodbatlas --atlas-public-key <key> --atlas-private-key <secret>
-```
-
-Alternatively, set API keys as environment variables:
-
-```bash
-export ATLAS_PUBLIC_KEY=<key>
-export ATLAS_PRIVATE_KEY=<secret>
-```
-
-Then run Prowler with the following command:
+#### Scan all projects and clusters
 
 ```bash
 prowler mongodbatlas
 ```
 
-### Scanning a Specific Project
+This command enumerates all projects accessible to the API key and scans every cluster.
 
-To scan a specific project, add the following argument to the command above:
+#### Scan a specific project
+
+Add the `--atlas-project-id` flag when you only want to assess one project:
 
 ```bash
 prowler mongodbatlas --atlas-project-id <project-id>
 ```
+
+### Additional tips
+
+- Combine flags (for example, `--checks` or `--services`) just like with other providers.
+- Use `--output-modes` to export findings in JSON, CSV, ASFF, etc.
+- Rotate API keys regularly and update the stored credentials in Prowler App to maintain connectivity.
+
+For more examples (filters, outputs, scheduling), refer back to the [MongoDB Atlas documentation hub](./authentication.mdx) and the main Prowler CLI usage guide.

mcp_server/.env.template

@@ -1,3 +1,3 @@
 PROWLER_APP_API_KEY="pk_your_api_key_here"
-PROWLER_API_BASE_URL="https://api.prowler.com"
+API_BASE_URL="https://api.prowler.com/api/v1"
 PROWLER_MCP_TRANSPORT_MODE="stdio"

mcp_server/AGENTS.md

@@ -0,0 +1,310 @@
+# Prowler MCP Server - AI Agent Ruleset
+
+**Complete guide for AI agents and developers working on the Prowler MCP Server - the Model Context Protocol server that provides AI agents access to the Prowler ecosystem.**
+
+## Project Overview
+
+The Prowler MCP Server brings the entire Prowler ecosystem to AI assistants through
+the Model Context Protocol (MCP). It enables seamless integration with AI tools
+like Claude Desktop, Cursor, and other MCP hosts, allowing interaction with
+Prowler's security capabilities through natural language.
+
+---
+
+## Critical Rules
+
+### Tool Implementation
+
+- **ALWAYS**: Extend `BaseTool` ABC for new Prowler App tools (auto-registration)
+- **ALWAYS**: Use `@mcp.tool()` decorator for Hub/Docs tools (manual registration)
+- **NEVER**: Manually register BaseTool subclasses (auto-discovered via `load_all_tools()`)
+- **NEVER**: Import tools directly in server.py (tool_loader handles discovery)
+
+### Models
+
+- **ALWAYS**: Use `MinimalSerializerMixin` for LLM-optimized responses
+- **ALWAYS**: Implement `from_api_response()` factory method for API transformations
+- **ALWAYS**: Use two-tier models (Simplified for lists, Detailed for single items)
+- **NEVER**: Return raw API responses (transform to simplified models)
+
+### API Client
+
+- **ALWAYS**: Use singleton `ProwlerAPIClient` via `self.api_client` in tools
+- **ALWAYS**: Use `build_filter_params()` for query parameter normalization
+- **NEVER**: Create new httpx clients in tools (use shared client)
+
+---
+
+## Architecture
+
+### Three Sub-Servers Pattern
+
+The main server (`server.py`) orchestrates three independent sub-servers with prefixed tool namespacing:
+
+```python
+# server.py imports sub-servers with prefixes
+await prowler_mcp_server.import_server(hub_mcp_server, prefix="prowler_hub")
+await prowler_mcp_server.import_server(app_mcp_server, prefix="prowler_app")
+await prowler_mcp_server.import_server(docs_mcp_server, prefix="prowler_docs")
+```
+
+This pattern ensures:
+- Failures in one sub-server do not block others
+- Clear tool namespacing for LLM disambiguation
+- Independent development and testing
+
+### Tool Naming Convention
+
+All tools follow a consistent naming pattern with prefixes:
+- `prowler_hub_*` - Prowler Hub catalog and compliance tools
+- `prowler_docs_*` - Prowler documentation search and retrieval
+- `prowler_app_*` - Prowler Cloud and App (Self-Managed) management tools
+
+### Tool Registration Patterns
+
+**Pattern 1: Prowler Hub/Docs (Direct Decorators)**
+
+```python
+# prowler_hub/server.py or prowler_documentation/server.py
+hub_mcp_server = FastMCP("prowler-hub")
+
+@hub_mcp_server.tool()
+async def get_checks(providers: str | None = None) -> dict:
+    """Tool docstring becomes LLM description."""
+    # Direct implementation
+    response = prowler_hub_client.get("/check", params=params)
+    return response.json()
+```
+
+**Pattern 2: Prowler App (BaseTool Auto-Registration)**
+
+```python
+# prowler_app/tools/findings.py
+class FindingsTools(BaseTool):
+    async def search_security_findings(
+        self,
+        severity: list[str] = Field(default=[], description="Filter by severity")
+    ) -> dict:
+        """Docstring becomes LLM description."""
+        response = await self.api_client.get("/api/v1/findings")
+        return SimplifiedFinding.from_api_response(response).model_dump()
+```
+
+NOTE: Only public methods of `BaseTool` subclasses are registered as tools.
+
+---
+
+## Tech Stack
+
+- **Language**: Python 3.12+
+- **MCP Framework**: FastMCP 2.13.1
+- **HTTP Client**: httpx (async)
+- **Validation**: Pydantic with MinimalSerializerMixin
+- **Package Manager**: uv
+
+---
+
+## Project Structure
+
+```
+mcp_server/
+├── README.md                              # User documentation
+├── AGENTS.md                              # This file - AI agent guidelines
+├── CHANGELOG.md                           # Version history
+├── pyproject.toml                         # Project metadata and dependencies
+├── Dockerfile                             # Container image definition
+├── entrypoint.sh                          # Docker entrypoint script
+└── prowler_mcp_server/
+    ├── __init__.py                        # Version info
+    ├── main.py                            # CLI entry point
+    ├── server.py                          # Main FastMCP server orchestration
+    ├── lib/
+    │   └── logger.py                      # Structured logging
+    ├── prowler_hub/
+    │   └── server.py                      # Hub tools (10 tools, no auth)
+    ├── prowler_app/
+    │   ├── server.py                      # App server initialization
+    │   ├── tools/
+    │   │   ├── base.py                    # BaseTool abstract class
+    │   │   ├── findings.py                # Findings tools
+    │   │   ├── providers.py               # Provider tools
+    │   │   ├── scans.py                   # Scan tools
+    │   │   ├── resources.py               # Resource tools
+    │   │   └── muting.py                  # Muting tools
+    │   ├── models/
+    │   │   ├── base.py                    # MinimalSerializerMixin
+    │   │   ├── findings.py                # Finding models
+    │   │   ├── providers.py               # Provider models
+    │   │   ├── scans.py                   # Scan models
+    │   │   ├── resources.py               # Resource models
+    │   │   └── muting.py                  # Muting models
+    │   └── utils/
+    │       ├── api_client.py              # ProwlerAPIClient singleton
+    │       ├── auth.py                    # ProwlerAppAuth (STDIO/HTTP)
+    │       └── tool_loader.py             # Auto-discovery and registration
+    └── prowler_documentation/
+        ├── server.py                      # Documentation tools (2 tools, no auth)
+        └── search_engine.py               # Mintlify API integration
+```
+
+---
+
+## Commands
+
+NOTE: To run a python command always use `uv run <command>` from within the `mcp_server/` directory.
+
+### Development
+
+```bash
+# Navigate to MCP server directory
+cd mcp_server
+
+# Run in STDIO mode (default)
+uv run prowler-mcp
+
+# Run in HTTP mode
+uv run prowler-mcp --transport http --host 0.0.0.0 --port 8000
+
+# Run from anywhere using uvx
+uvx /path/to/prowler/mcp_server/
+```
+
+---
+
+## Development Patterns
+
+### Adding New Tools to Prowler App
+
+1. **Create or extend a tool class** in `prowler_app/tools/`:
+
+```python
+# prowler_app/tools/new_feature.py
+from pydantic import Field
+from prowler_mcp_server.prowler_app.tools.base import BaseTool
+from prowler_mcp_server.prowler_app.models.new_feature import FeatureResponse
+
+class NewFeatureTools(BaseTool):
+    async def list_features(
+        self,
+        status: str | None = Field(default=None, description="Filter by status")
+    ) -> dict:
+        """List all features with optional filtering.
+
+        Returns a simplified list of features optimized for LLM consumption.
+        """
+        params = {}
+        if status:
+            params["filter[status]"] = status
+
+        clean_params = self.api_client.build_filter_params(params)
+        response = await self.api_client.get("/api/v1/features", params=clean_params)
+
+        return FeatureResponse.from_api_response(response).model_dump()
+```
+
+2. **Create corresponding models** in `prowler_app/models/`:
+
+```python
+# prowler_app/models/new_feature.py
+from pydantic import Field
+from prowler_mcp_server.prowler_app.models.base import MinimalSerializerMixin
+
+class SimplifiedFeature(MinimalSerializerMixin):
+    """Lightweight feature for list operations."""
+    id: str
+    name: str
+    status: str
+
+class DetailedFeature(SimplifiedFeature):
+    """Extended feature with complete details."""
+    description: str | None = None
+    created_at: str
+    updated_at: str
+
+    @classmethod
+    def from_api_response(cls, data: dict) -> "DetailedFeature":
+        """Transform API response to model."""
+        attributes = data.get("attributes", {})
+        return cls(
+            id=data["id"],
+            name=attributes["name"],
+            status=attributes["status"],
+            description=attributes.get("description"),
+            created_at=attributes["created_at"],
+            updated_at=attributes["updated_at"],
+        )
+```
+
+3. **No registration needed** - the tool loader auto-discovers BaseTool subclasses
+
+### Adding Tools to Prowler Hub/Docs
+
+Use the `@mcp.tool()` decorator directly:
+
+```python
+# prowler_hub/server.py
+@hub_mcp_server.tool()
+async def new_hub_tool(param: str) -> dict:
+    """Tool description for LLM."""
+    response = prowler_hub_client.get("/endpoint")
+    return response.json()
+```
+
+---
+
+## Code Quality Standards
+
+### Tool Docstrings
+
+Tool docstrings become AI agent descriptions. Write them in a clear, concise manner focusing on LLM-relevant behavior:
+
+```python
+async def search_security_findings(
+    self,
+    severity: list[str] = Field(default=[], description="Filter by severity levels")
+) -> dict:
+    """Search security findings with advanced filtering.
+
+    Returns a lightweight list of findings optimized for LLM consumption.
+    Use get_finding_details for complete information about a specific finding.
+    """
+```
+
+### Model Design
+
+- Use `MinimalSerializerMixin` to exclude None/empty values
+- Implement `from_api_response()` for consistent API transformation
+- Create two-tier models: Simplified (lists) and Detailed (single items)
+
+### Error Handling
+
+Return structured error responses rather than raising exceptions:
+
+```python
+try:
+    response = await self.api_client.get(f"/api/v1/items/{item_id}")
+    return DetailedItem.from_api_response(response["data"]).model_dump()
+except Exception as e:
+    self.logger.error(f"Failed to get item {item_id}: {e}")
+    return {"error": str(e), "status": "failed"}
+```
+
+---
+
+## QA Checklist Before Commit
+
+- [ ] Tool docstrings are clear and describe LLM-relevant behavior
+- [ ] Models use `MinimalSerializerMixin` for LLM optimization
+- [ ] API responses are transformed to simplified models
+- [ ] No hardcoded secrets or API keys
+- [ ] Error handling returns structured responses
+- [ ] New tools are auto-discovered (BaseTool subclass) or properly decorated
+- [ ] Parameter descriptions use Pydantic `Field()` with clear descriptions
+
+---
+
+## References
+
+- **Root Project Guide**: `../AGENTS.md`
+- **FastMCP Documentation**: https://gofastmcp.com/llms.txt
+- **Prowler API Documentation**: https://api.prowler.com/api/v1/docs

mcp_server/CHANGELOG.md

@@ -2,6 +2,17 @@
 
 All notable changes to the **Prowler MCP Server** are documented in this file.
 
+## [0.3.0] (Prowler v5.16.0)
+
+### Added
+
+- Add new MCP Server tools for Prowler Compliance Framework Management [(#9568)](https://github.com/prowler-cloud/prowler/pull/9568)
+
+### Changed
+
+- Update API base URL environment variable to include complete path [(#9542)](https://github.com/prowler-cloud/prowler/pull/9542)
+- Standardize Prowler Hub and Docs tools format for AI optimization [(#9578)](https://github.com/prowler-cloud/prowler/pull/9578)
+
 ## [0.2.0] (Prowler v5.15.0)
 
 ### Added

mcp_server/README.md

@@ -1,18 +1,60 @@
 # Prowler MCP Server
 
-> ⚠️ **Preview Feature**: This MCP server is currently in preview and under active development. Features and functionality may change. We welcome your feedback—please report any issues on [GitHub](https://github.com/prowler-cloud/prowler/issues) or join our [Slack community](https://goto.prowler.com/slack) to discuss and share your thoughts.
+**Prowler MCP Server** brings the entire Prowler ecosystem to AI assistants through the [Model Context Protocol (MCP)](https://modelcontextprotocol.io). It enables seamless integration with AI tools like Claude Desktop, Cursor, and other MCP clients, allowing interaction with Prowler's security capabilities through natural language.
 
-Access the entire Prowler ecosystem through the Model Context Protocol (MCP). This server provides three main capabilities:
+> **Preview Feature**: This MCP server is currently under active development. Features and functionality may change. We welcome your feedback—please report any issues on [GitHub](https://github.com/prowler-cloud/prowler/issues) or join our [Slack community](https://goto.prowler.com/slack).
 
-- **Prowler Cloud and Prowler App (Self-Managed)**: Full access to Prowler Cloud platform and Prowler Self-Managed for managing providers, running scans, and analyzing security findings
-- **Prowler Hub**: Access to Prowler's security checks, fixers, and compliance frameworks catalog
-- **Prowler Documentation**: Search and retrieve official Prowler documentation
+## Key Capabilities
 
-## Quick Start with Hosted Server (Recommended)
+### Prowler Cloud and Prowler App (Self-Managed)
 
-**The easiest way to use Prowler MCP is through our hosted server at `https://mcp.prowler.com/mcp`**
+Full access to Prowler Cloud platform and self-managed Prowler App for:
+- **Findings Analysis**: Query, filter, and analyze security findings across all your cloud environments
+- **Provider Management**: Create, configure, and manage your configured Prowler providers (AWS, Azure, GCP, etc.)
+- **Scan Orchestration**: Trigger on-demand scans and schedule recurring security assessments
+- **Resource Inventory**: Search and view detailed information about your audited resources
+- **Muting Management**: Create and manage muting rules to suppress non-critical findings
+- **Compliance Reporting**: View compliance status across frameworks and drill into requirement-level details
 
-No installation required! Just configure your MCP client:
+### Prowler Hub
+
+Access to Prowler's comprehensive security knowledge base:
+- **Security Checks Catalog**: Browse and search **over 1000 security checks** across multiple Prowler providers
+- **Check Implementation**: View the Python code that powers each security check
+- **Automated Fixers**: Access remediation scripts for common security issues
+- **Compliance Frameworks**: Explore mappings to **over 70 compliance standards and frameworks**
+- **Provider Services**: View available services and checks for all supported Prowler providers
+
+### Prowler Documentation
+
+Search and retrieve official Prowler documentation:
+- **Intelligent Search**: Full-text search across all Prowler documentation
+- **Contextual Results**: Get relevant documentation pages with highlighted snippets
+- **Document Retrieval**: Access complete markdown content of any documentation file
+
+## Documentation
+
+For comprehensive guides and tutorials, see the official documentation:
+
+| Guide | Description |
+|-------|-------------|
+| [Overview](https://docs.prowler.com/getting-started/products/prowler-mcp) | Key capabilities, use cases, and deployment options |
+| [Installation](https://docs.prowler.com/getting-started/installation/prowler-mcp) | Docker, PyPI, and source installation |
+| [Configuration](https://docs.prowler.com/getting-started/basic-usage/prowler-mcp) | Configure Claude Desktop, Cursor, and other MCP clients |
+| [Tools Reference](https://docs.prowler.com/getting-started/basic-usage/prowler-mcp-tools) | Complete reference of all tools |
+| [Developer Guide](https://docs.prowler.com/developer-guide/mcp-server) | How to extend with new tools |
+
+## Deployment Options
+
+Prowler MCP Server can be used in three ways:
+
+### 1. Prowler Cloud MCP Server (Recommended)
+
+**Use Prowler's managed MCP server at `https://mcp.prowler.com/mcp`**
+
+- No installation required
+- Managed and maintained by Prowler team
+- Always up-to-date
 
 ```json
 {
@@ -30,70 +72,37 @@ No installation required! Just configure your MCP client:
 }
 ```
 
-**Configuration file locations:**
-- **Claude Desktop (macOS)**: `~/Library/Application Support/Claude/claude_desktop_config.json`
-- **Claude Desktop (Windows)**: `%AppData%\Claude\claude_desktop_config.json`
-- **Cursor**: `~/.cursor/mcp.json`
+### 2. Local STDIO Mode
 
-Get your API key at [Prowler Cloud](https://cloud.prowler.com) → Settings → API Keys
+**Run the server locally on your machine**
 
-> **Benefits:** Always up-to-date, no maintenance, managed by Prowler team
+- Runs as a subprocess of your MCP client
+- Requires Python 3.12+ or Docker
 
-## Local/Self-Hosted Installation
+### 3. Self-Hosted HTTP Mode
 
-If you need to run the MCP server locally or self-host it, choose one of the following installation methods. **Configuration is the same** for both managed and local installations - just point to your local server URL instead of `https://mcp.prowler.com/mcp`.
+**Deploy your own remote MCP server**
 
-### Requirements
+- Full control over deployment
+- Requires Python 3.12+ or Docker
 
-- Python 3.12+ (for source/PyPI installation)
-- Docker (for Docker installation)
-- Network access to `https://hub.prowler.com` (for Prowler Hub)
-- Network access to `https://prowler.mintlify.app` (for Prowler Documentation)
-- Network access to Prowler Cloud and Prowler App (Self-Managed) API (optional, only for Prowler Cloud/App features)
-- Prowler Cloud account credentials (only for Prowler Cloud and Prowler App features)
+See the [Installation Guide](https://docs.prowler.com/getting-started/installation/prowler-mcp) for complete instructions.
 
-### Installation Methods
+## Quick Installation
 
-#### Option 1: Docker Hub (Recommended)
-
-Pull the official image from Docker Hub:
+### Docker (Recommended)
 
 ```bash
 docker pull prowlercloud/prowler-mcp
-```
 
-Run in STDIO mode:
-```bash
+# STDIO mode
 docker run --rm -i prowlercloud/prowler-mcp
+
+# HTTP mode
+docker run --rm -p 8000:8000 prowlercloud/prowler-mcp --transport http --host 0.0.0.0 --port 8000
 ```
 
-Run in HTTP mode:
-```bash
-docker run --rm -p 8000:8000 \
-  prowlercloud/prowler-mcp \
-  --transport http --host 0.0.0.0 --port 8000
-```
-
-With environment variables:
-```bash
-docker run --rm -i \
-  -e PROWLER_APP_API_KEY="pk_your_api_key" \
-  -e PROWLER_API_BASE_URL="https://api.prowler.com" \
-  prowlercloud/prowler-mcp
-```
-
-**Docker Hub:** [prowlercloud/prowler-mcp](https://hub.docker.com/r/prowlercloud/prowler-mcp)
-
-#### Option 2: PyPI Package (Coming Soon)
-
-```bash
-pip install prowler-mcp-server
-prowler-mcp --help
-```
-
-#### Option 3: From Source (Development)
-
-Clone the repository and use `uv`:
+### From Source
 
 ```bash
 git clone https://github.com/prowler-cloud/prowler.git
@@ -101,400 +110,86 @@ cd prowler/mcp_server
 uv run prowler-mcp --help
 ```
 
-Install [uv](https://docs.astral.sh/uv/) first if needed.
-
-#### Option 4: Build Docker Image from Source
-
-```bash
-git clone https://github.com/prowler-cloud/prowler.git
-cd prowler/mcp_server
-docker build -t prowler-mcp .
-docker run --rm -i prowler-mcp
-```
-
-## Running
-
-The Prowler MCP server supports two transport modes:
-- **STDIO mode** (default): For direct integration with MCP clients like Claude Desktop
-- **HTTP mode**: For remote access over HTTP with Bearer token authentication
-
-### Transport Modes
-
-#### STDIO Mode (Default)
-
-STDIO mode is the standard MCP transport for direct client integration:
-
-```bash
-cd prowler/mcp_server
-uv run prowler-mcp
-# or
-uv run prowler-mcp --transport stdio
-```
-
-#### HTTP Mode (Remote Server)
-
-HTTP mode allows the server to run as a remote service accessible over HTTP:
-
-```bash
-cd prowler/mcp_server
-# Run on default host and port (127.0.0.1:8000)
-uv run prowler-mcp --transport http
-
-# Run on custom host and port
-uv run prowler-mcp --transport http --host 0.0.0.0 --port 8080
-```
-
-For self-deployed MCP remote server, you can use also configure the server to use a custom API base URL with the environment variable `PROWLER_API_BASE_URL`; and the transport mode with the environment variable `PROWLER_MCP_TRANSPORT_MODE`.
-
-```bash
-export PROWLER_API_BASE_URL="https://api.prowler.com"
-export PROWLER_MCP_TRANSPORT_MODE="http"
-```
-
-### Using uv directly
-
-After installation, start the MCP server via the console script:
-
-```bash
-cd prowler/mcp_server
-uv run prowler-mcp
-```
-
-Alternatively, you can run from wherever you want using `uvx` command:
-
-```bash
-uvx /path/to/prowler/mcp_server/
-```
-
-### Using Docker
-
-#### STDIO Mode (Default)
-
-Run the pre-built Docker container in STDIO mode:
-
-```bash
-cd prowler/mcp_server
-docker run --rm --env-file ./.env -it prowler-mcp
-```
-
-#### HTTP Mode (Remote Server)
-
-Run as a remote HTTP server:
-
-```bash
-cd prowler/mcp_server
-# Run on port 8000 (accessible from host)
-docker run --rm --env-file ./.env -p 8000:8000 -it prowler-mcp --transport http --host 0.0.0.0 --port 8000
-
-# Run on custom port
-docker run --rm --env-file ./.env -p 8080:8080 -it prowler-mcp --transport http --host 0.0.0.0 --port 8080
-```
-
-## Production Deployment
-
-For production deployments that require customization, it is recommended to use the ASGI application that can be found in `prowler_mcp_server.server`. This can be run with uvicorn:
-
-```bash
-uvicorn prowler_mcp_server.server:app --host 0.0.0.0 --port 8000
-```
-
-For more details on production deployment options, see the [FastMCP production deployment guide](https://gofastmcp.com/deployment/http#production-deployment) and [uvicorn settings](https://www.uvicorn.org/settings/).
-
-## Command Line Arguments
-
-The Prowler MCP server supports the following command line arguments:
-
-```
-prowler-mcp [--transport {stdio,http}] [--host HOST] [--port PORT]
-```
-
-**Arguments:**
-- `--transport {stdio,http}`: Transport method (default: stdio)
-  - `stdio`: Standard input/output transport for direct MCP client integration
-  - `http`: HTTP transport for remote server access
-- `--host HOST`: Host to bind to for HTTP transport (default: 127.0.0.1)
-- `--port PORT`: Port to bind to for HTTP transport (default: 8000)
-
-**Examples:**
-```bash
-# Default STDIO mode
-prowler-mcp
-
-# Explicit STDIO mode
-prowler-mcp --transport stdio
-
-# HTTP mode with default host and port (127.0.0.1:8000)
-prowler-mcp --transport http
-
-# HTTP mode accessible from any network interface
-prowler-mcp --transport http --host 0.0.0.0
-
-# HTTP mode with custom port
-prowler-mcp --transport http --host 0.0.0.0 --port 8080
-```
-
 ## Available Tools
 
-### Prowler Hub
+For complete tool descriptions and parameters, see the [Tools Reference](https://docs.prowler.com/getting-started/basic-usage/prowler-mcp-tools).
 
-All tools are exposed under the `prowler_hub` prefix.
+### Tool Naming Convention
 
-- `prowler_hub_get_check_filters`: Return available filter values for checks (providers, services, severities, categories, compliances). Call this before `prowler_hub_get_checks` to build valid queries.
-- `prowler_hub_get_checks`: List checks with option of advanced filtering.
-- `prowler_hub_get_check_raw_metadata`: Fetch raw check metadata JSON (low-level version of get_checks).
-- `prowler_hub_get_check_code`: Fetch check implementation Python code from Prowler.
-- `prowler_hub_get_check_fixer`: Fetch check fixer Python code from Prowler (if it exists).
-- `prowler_hub_search_checks`: Full‑text search across check metadata.
-- `prowler_hub_get_compliance_frameworks`: List/filter compliance frameworks.
-- `prowler_hub_search_compliance_frameworks`: Full-text search across frameworks.
-- `prowler_hub_list_providers`: List Prowler official providers and their services.
-- `prowler_hub_get_artifacts_count`: Return total artifact count (checks + frameworks).
+All tools follow a consistent naming pattern with prefixes:
+- `prowler_app_*` - Prowler Cloud and App (Self-Managed) management tools
+- `prowler_hub_*` - Prowler Hub catalog and compliance tools
+- `prowler_docs_*` - Prowler documentation search and retrieval
 
-### Prowler Documentation
+## Architecture
 
-All tools are exposed under the `prowler_docs` prefix.
-
-- `prowler_docs_search`: Search the official Prowler documentation using fulltext search. Returns relevant documentation pages with highlighted snippets and relevance scores.
-- `prowler_docs_get_document`: Retrieve the full markdown content of a specific documentation file using the path from search results.
-
-### Prowler Cloud and Prowler App (Self-Managed)
-
-All tools are exposed under the `prowler_app` prefix.
-
-#### Findings Management
-- `prowler_app_list_findings`: List security findings from Prowler scans with advanced filtering
-- `prowler_app_get_finding`: Get detailed information about a specific security finding
-- `prowler_app_get_latest_findings`: Retrieve latest findings from the latest scans for each provider
-- `prowler_app_get_findings_metadata`: Fetch unique metadata values from filtered findings
-- `prowler_app_get_latest_findings_metadata`: Fetch metadata from latest findings across all providers
-
-#### Provider Management
-- `prowler_app_list_providers`: List all providers with filtering options
-- `prowler_app_create_provider`: Create a new provider in the current tenant
-- `prowler_app_get_provider`: Get detailed information about a specific provider
-- `prowler_app_update_provider`: Update provider details (alias, etc.)
-- `prowler_app_delete_provider`: Delete a specific provider
-- `prowler_app_test_provider_connection`: Test provider connection status
-
-#### Provider Secrets Management
-- `prowler_app_list_provider_secrets`: List all provider secrets with filtering
-- `prowler_app_add_provider_secret`: Add or update credentials for a provider
-- `prowler_app_get_provider_secret`: Get detailed information about a provider secret
-- `prowler_app_update_provider_secret`: Update provider secret details
-- `prowler_app_delete_provider_secret`: Delete a provider secret
-
-#### Scan Management
-- `prowler_app_list_scans`: List all scans with filtering options
-- `prowler_app_create_scan`: Trigger a manual scan for a specific provider
-- `prowler_app_get_scan`: Get detailed information about a specific scan
-- `prowler_app_update_scan`: Update scan details
-- `prowler_app_get_scan_compliance_report`: Download compliance report as CSV
-- `prowler_app_get_scan_report`: Download ZIP file containing scan report
-
-#### Schedule Management
-- `prowler_app_schedules_daily_scan`: Create a daily scheduled scan for a provider
-
-#### Processor Management
-- `prowler_app_processors_list`: List all processors with filtering
-- `prowler_app_processors_create`: Create a new processor. For now, only mute lists are supported.
-- `prowler_app_processors_retrieve`: Get processor details by ID
-- `prowler_app_processors_partial_update`: Update processor configuration
-- `prowler_app_processors_destroy`: Delete a processor
-
-## Configuration
-
-### Prowler Cloud and Prowler App (Self-Managed) Authentication
-
-> [!IMPORTANT]
-> Authentication is not needed for using Prowler Hub or Prowler Documentation features.
-
-The Prowler MCP server supports different authentication in Prowler Cloud and Prowler App (Self-Managed) methods depending on the transport mode:
-
-#### STDIO Mode Authentication
-
-For STDIO mode, authentication is handled via environment variables using an API key:
-
-```bash
-# Required for Prowler Cloud and Prowler App (Self-Managed) authentication
-export PROWLER_APP_API_KEY="pk_your_api_key_here"
-
-# Optional - for custom API endpoint, in case not provided Prowler Cloud API will be used
-export PROWLER_API_BASE_URL="https://api.prowler.com"
+```
+prowler_mcp_server/
+├── server.py                 # Main orchestrator (imports sub-servers with prefixes)
+├── main.py                   # CLI entry point
+├── prowler_hub/              # tools - no authentication required
+├── prowler_app/              # tools - authentication required
+│   ├── tools/                # Tool implementations
+│   ├── models/               # Pydantic models for LLM-optimized responses
+│   └── utils/                # API client, authentication, tool loader
+└── prowler_documentation/    # tools - no authentication required
 ```
 
-#### HTTP Mode Authentication
+**Key Features:**
+- **Modular Design**: Three independent sub-servers with prefixed namespacing
+- **Auto-Discovery**: Prowler App tools are automatically discovered and registered
+- **LLM Optimization**: Response models minimize token usage by excluding empty values
+- **Dual Transport**: Supports both STDIO (local) and HTTP (remote) modes
 
-For HTTP mode (remote server), authentication is handled via Bearer tokens. The MCP server supports both JWT tokens and API keys:
+## Use Cases
 
-**Option 1: Using API Keys (Recommended)**
-Use your Prowler API key directly in the MCP client configuration with Bearer token format:
-```
-Authorization: Bearer pk_your_api_key_here
-```
+The Prowler MCP Server enables powerful workflows through AI assistants:
 
-**Option 2: Using JWT Tokens**
-You need to obtain a JWT token from Prowler Cloud/App and include the generated token in the MCP client configuration. To get a valid token, you can use the following command (replace the email and password with your own credentials):
+**Security Operations**
+- "Show me all critical findings from my AWS production accounts"
+- "Register my new AWS account in Prowler and run a scheduled scan every day"
+- "List all muted findings and detect what findgings are muted by a not enough good reason in relation to their severity"
 
-```bash
-curl -X POST https://api.prowler.com/api/v1/tokens \
-  -H "Content-Type: application/vnd.api+json" \
-  -H "Accept: application/vnd.api+json" \
-  -d '{
-    "data": {
-      "type": "tokens",
-      "attributes": {
-        "email": "your-email@example.com",
-        "password": "your-password"
-      }
-    }
-  }'
-```
+**Security Research**
+- "Explain what the S3 bucket public access Prowler check does"
+- "Find all Prowler checks related to encryption at rest"
+- "What is the latest version of the CIS that Prowler is covering per provider?"
 
-The response will be a JWT token that you can use to [authenticate your MCP client](#http-mode-configuration-remote-server).
+**Documentation & Learning**
+- "How do I configure Prowler to scan my GCP organization?"
+- "What authentication methods does Prowler support for Azure?"
+- "How can I contribute with a new security check to Prowler?"
 
-### MCP Client Configuration
+## Requirements
 
-Configure your MCP client, like Claude Desktop, Cursor, etc, to connect to the server. The configuration depends on whether you're running in STDIO mode (local) or HTTP mode (remote).
+**For Prowler Cloud MCP Server:**
+- Prowler Cloud account and API key (only for Prowler Cloud/App features)
 
-#### STDIO Mode Configuration
+**For self-hosted STDIO/HTTP Mode:**
+- Python 3.12+ or Docker
+- Network access to:
+  - `https://hub.prowler.com` (for Prowler Hub)
+  - `https://docs.prowler.com` (for Prowler Documentation)
+  - Prowler Cloud API or self-hosted Prowler App API (for Prowler Cloud/App features)
 
-For local execution, configure your MCP client to launch the server directly. Below are examples for both direct execution and Docker deployment; consult your client's documentation for exact locations.
+> **No Authentication Required**: Prowler Hub and Prowler Documentation features work without authentication. A Prowler API key is only required to access Prowler Cloud or Prowler App (Self-Managed) features.
 
-##### Using uvx (Direct Execution)
+## Configuring MCP Hosts
 
-```json
-{
-  "mcpServers": {
-    "prowler": {
-      "command": "uvx",
-      "args": ["/path/to/prowler/mcp_server/"],
-      "env": {
-        "PROWLER_APP_API_KEY": "pk_your_api_key_here",
-        "PROWLER_API_BASE_URL": "https://api.prowler.com"  // Optional, in case not provided Prowler Cloud API will be used
-      }
-    }
-  }
-}
-```
+To configure your MCP host (Claude Code, Cursor, etc.) see the [Configuration Guide](https://docs.prowler.com/getting-started/basic-usage/prowler-mcp) for detailed setup instructions.
 
-##### Using Docker
+## Contributing
 
-```json
-{
-  "mcpServers": {
-    "prowler": {
-      "command": "docker",
-      "args": [
-        "run", "--rm", "-i",
-        "--env", "PROWLER_APP_API_KEY=pk_your_api_key_here",
-        "--env", "PROWLER_API_BASE_URL=https://api.prowler.com",  // Optional, in case not provided Prowler Cloud API will be used
-        "prowler-mcp"
-      ]
-    }
-  }
-}
-```
+For developers looking to extend the MCP server with new tools or features:
 
-#### HTTP Mode Configuration (Remote Server)
+- **[Developer Guide](https://docs.prowler.com/developer-guide/mcp-server)**: Step-by-step instructions for adding new tools
+- **[AGENTS.md](./AGENTS.md)**: AI agent guidelines and coding patterns
 
-For HTTP mode, you can configure your MCP client to connect to a remote Prowler MCP server.
+## Related Products
 
-Most MCP clients don't natively support HTTP transport with Bearer token authentication. However, you can use the `mcp-remote` proxy tool to connect any MCP client to remote HTTP servers.
-
-##### Using mcp-remote Proxy (Recommended for Claude Desktop)
-
-For clients like Claude Desktop that don't support HTTP transport natively, use the `mcp-remote` npm package as a proxy:
-
-**Using API Key (Recommended):**
-```json
-{
-  "mcpServers": {
-    "prowler": {
-      "command": "npx",
-      "args": [
-        "mcp-remote",
-        "https://mcp.prowler.com/mcp",
-        "--header",
-        "Authorization: Bearer pk_your_api_key_here"
-      ]
-    }
-  }
-}
-```
-
-**Using JWT Token:**
-```json
-{
-  "mcpServers": {
-    "prowler": {
-      "command": "npx",
-      "args": [
-        "mcp-remote",
-        "https://mcp.prowler.com/mcp",
-        "--header",
-        "Authorization: Bearer <your-jwt-token-here>"
-      ]
-    }
-  }
-}
-```
-
-> **Note:** Replace `https://mcp.prowler.com/mcp` with your actual MCP server URL (use `http://localhost:8000/mcp` for local deployment). The `mcp-remote` package is automatically installed by `npx` on first use.
-
-> **Info:** The `mcp-remote` tool acts as a bridge, converting STDIO protocol (used by Claude Desktop) to HTTP requests (used by the remote MCP server). Learn more at [mcp-remote on npm](https://www.npmjs.com/package/mcp-remote).
-
-##### Direct HTTP Configuration (For Compatible Clients)
-
-For clients that natively support HTTP transport with Bearer token authentication:
-
-**Using API Key:**
-```json
-{
-  "mcpServers": {
-    "prowler": {
-      "url": "https://mcp.prowler.com/mcp",
-      "headers": {
-        "Authorization": "Bearer pk_your_api_key_here"
-      }
-    }
-  }
-}
-```
-
-**Using JWT Token:**
-```json
-{
-  "mcpServers": {
-    "prowler": {
-      "url": "https://mcp.prowler.com/mcp",
-      "headers": {
-        "Authorization": "Bearer <your-jwt-token-here>"
-      }
-    }
-  }
-}
-```
-
-> **Note:** Replace `mcp.prowler.com` with your actual server hostname and adjust the port if needed (e.g., `http://localhost:8000/mcp` for local deployment).
-
-### Claude Desktop (macOS/Windows)
-
-Add the example server to Claude Desktop's config file, then restart the app.
-
-- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
-- Windows: `%AppData%\Claude\claude_desktop_config.json` (e.g. `C:\\Users\\<you>\\AppData\\Roaming\\Claude\\claude_desktop_config.json`)
-
-### Cursor (macOS/Linux)
-
-If you want to have it globally available, add the example server to Cursor's config file, then restart the app.
-
-- macOS/Linux: `~/.cursor/mcp.json`
-
-If you want to have it only for the current project, add the example server to the project's root in a new `.cursor/mcp.json` file.
-
-## Documentation
-
-For detailed documentation about the Prowler MCP Server, including guides, tutorials, and use cases, visit the [official Prowler documentation](https://docs.prowler.com).
+- **[Prowler Hub](https://hub.prowler.com)**: Browse security checks and compliance frameworks
+- **[Prowler Cloud](https://cloud.prowler.com)**: Managed Prowler platform
+- **[Lighthouse AI](https://docs.prowler.com/getting-started/products/prowler-lighthouse-ai)**: AI security analyst
 
 ## License
 

mcp_server/prowler_mcp_server/prowler_app/models/compliance.py

@@ -0,0 +1,240 @@
+"""Pydantic models for simplified compliance responses."""
+
+from typing import Any, Literal
+
+from prowler_mcp_server.prowler_app.models.base import MinimalSerializerMixin
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    SerializerFunctionWrapHandler,
+    model_serializer,
+)
+
+
+class ComplianceRequirementAttribute(MinimalSerializerMixin, BaseModel):
+    """Requirement attributes including associated check IDs.
+
+    Used to map requirements to the checks that validate them.
+    """
+
+    model_config = ConfigDict(frozen=True)
+
+    id: str = Field(
+        description="Requirement identifier within the framework (e.g., '1.1', '2.1.1')"
+    )
+    name: str = Field(default="", description="Human-readable name of the requirement")
+    description: str = Field(
+        default="", description="Detailed description of the requirement"
+    )
+    check_ids: list[str] = Field(
+        default_factory=list,
+        description="List of Prowler check IDs that validate this requirement",
+    )
+
+    @classmethod
+    def from_api_response(cls, data: dict) -> "ComplianceRequirementAttribute":
+        """Transform JSON:API compliance requirement attributes response to simplified format."""
+        attributes = data.get("attributes", {})
+
+        # Extract check_ids from the nested attributes structure
+        nested_attributes = attributes.get("attributes", {})
+        check_ids = nested_attributes.get("check_ids", [])
+
+        return cls(
+            id=attributes.get("id", data.get("id", "")),
+            name=attributes.get("name", ""),
+            description=attributes.get("description", ""),
+            check_ids=check_ids if check_ids else [],
+        )
+
+
+class ComplianceRequirementAttributesListResponse(BaseModel):
+    """Response for compliance requirement attributes list with check_ids mappings."""
+
+    model_config = ConfigDict(frozen=True)
+
+    requirements: list[ComplianceRequirementAttribute] = Field(
+        description="List of requirements with their associated check IDs"
+    )
+    total_count: int = Field(description="Total number of requirements")
+
+    @classmethod
+    def from_api_response(
+        cls, response: dict
+    ) -> "ComplianceRequirementAttributesListResponse":
+        """Transform JSON:API response to simplified format."""
+        data = response.get("data", [])
+
+        requirements = [
+            ComplianceRequirementAttribute.from_api_response(item) for item in data
+        ]
+
+        return cls(
+            requirements=requirements,
+            total_count=len(requirements),
+        )
+
+
+class ComplianceFrameworkSummary(MinimalSerializerMixin, BaseModel):
+    """Simplified compliance framework overview for list operations.
+
+    Used by get_compliance_overview() to show high-level compliance status
+    per framework.
+    """
+
+    model_config = ConfigDict(frozen=True)
+
+    id: str = Field(description="Unique identifier for this compliance overview entry")
+    compliance_id: str = Field(
+        description="Compliance framework identifier (e.g., 'cis_1.5_aws', 'pci_dss_v4.0_aws')"
+    )
+    framework: str = Field(
+        description="Human-readable framework name (e.g., 'CIS', 'PCI-DSS', 'HIPAA')"
+    )
+    version: str = Field(description="Framework version (e.g., '1.5', '4.0')")
+    total_requirements: int = Field(
+        default=0, description="Total number of requirements in this framework"
+    )
+    requirements_passed: int = Field(
+        default=0, description="Number of requirements that passed"
+    )
+    requirements_failed: int = Field(
+        default=0, description="Number of requirements that failed"
+    )
+    requirements_manual: int = Field(
+        default=0, description="Number of requirements requiring manual verification"
+    )
+
+    @property
+    def pass_percentage(self) -> float:
+        """Calculate pass percentage based on passed requirements."""
+        if self.total_requirements == 0:
+            return 0.0
+        return round((self.requirements_passed / self.total_requirements) * 100, 1)
+
+    @property
+    def fail_percentage(self) -> float:
+        """Calculate fail percentage based on failed requirements."""
+        if self.total_requirements == 0:
+            return 0.0
+        return round((self.requirements_failed / self.total_requirements) * 100, 1)
+
+    @model_serializer(mode="wrap")
+    def _serialize(self, handler: SerializerFunctionWrapHandler) -> dict[str, Any]:
+        """Serialize with calculated percentages included."""
+        data = handler(self)
+        # Filter out None/empty values
+        data = {k: v for k, v in data.items() if v is not None and v != "" and v != []}
+        # Add calculated percentages
+        data["pass_percentage"] = self.pass_percentage
+        data["fail_percentage"] = self.fail_percentage
+        return data
+
+    @classmethod
+    def from_api_response(cls, data: dict) -> "ComplianceFrameworkSummary":
+        """Transform JSON:API compliance overview response to simplified format."""
+        attributes = data.get("attributes", {})
+
+        # The compliance_id field may be in attributes or use the "id" field from attributes
+        compliance_id = attributes.get("id", data.get("id", ""))
+
+        return cls(
+            id=data["id"],
+            compliance_id=compliance_id,
+            framework=attributes.get("framework", ""),
+            version=attributes.get("version", ""),
+            total_requirements=attributes.get("total_requirements", 0),
+            requirements_passed=attributes.get("requirements_passed", 0),
+            requirements_failed=attributes.get("requirements_failed", 0),
+            requirements_manual=attributes.get("requirements_manual", 0),
+        )
+
+
+class ComplianceRequirement(MinimalSerializerMixin, BaseModel):
+    """Individual compliance requirement with its status.
+
+    Used by get_compliance_framework_state_details() to show requirement-level breakdown.
+    """
+
+    model_config = ConfigDict(frozen=True)
+
+    id: str = Field(
+        description="Requirement identifier within the framework (e.g., '1.1', '2.1.1')"
+    )
+    description: str = Field(
+        description="Human-readable description of the requirement"
+    )
+    status: Literal["FAIL", "PASS", "MANUAL"] = Field(
+        description="Requirement status: FAIL (not compliant), PASS (compliant), MANUAL (requires manual verification)"
+    )
+
+    @classmethod
+    def from_api_response(cls, data: dict) -> "ComplianceRequirement":
+        """Transform JSON:API compliance requirement response to simplified format."""
+        attributes = data.get("attributes", {})
+
+        return cls(
+            id=attributes.get("id", data.get("id", "")),
+            description=attributes.get("description", ""),
+            status=attributes.get("status", "MANUAL"),
+        )
+
+
+class ComplianceFrameworksListResponse(BaseModel):
+    """Response for compliance frameworks list with aggregated statistics."""
+
+    model_config = ConfigDict(frozen=True)
+
+    frameworks: list[ComplianceFrameworkSummary] = Field(
+        description="List of compliance frameworks with their status"
+    )
+    total_count: int = Field(description="Total number of frameworks returned")
+
+    @classmethod
+    def from_api_response(cls, response: dict) -> "ComplianceFrameworksListResponse":
+        """Transform JSON:API response to simplified format."""
+        data = response.get("data", [])
+
+        frameworks = [
+            ComplianceFrameworkSummary.from_api_response(item) for item in data
+        ]
+
+        return cls(
+            frameworks=frameworks,
+            total_count=len(frameworks),
+        )
+
+
+class ComplianceRequirementsListResponse(BaseModel):
+    """Response for compliance requirements list queries."""
+
+    model_config = ConfigDict(frozen=True)
+
+    requirements: list[ComplianceRequirement] = Field(
+        description="List of requirements with their status"
+    )
+    total_count: int = Field(description="Total number of requirements")
+    passed_count: int = Field(description="Number of requirements with PASS status")
+    failed_count: int = Field(description="Number of requirements with FAIL status")
+    manual_count: int = Field(description="Number of requirements with MANUAL status")
+
+    @classmethod
+    def from_api_response(cls, response: dict) -> "ComplianceRequirementsListResponse":
+        """Transform JSON:API response to simplified format."""
+        data = response.get("data", [])
+
+        requirements = [ComplianceRequirement.from_api_response(item) for item in data]
+
+        # Calculate counts
+        passed = sum(1 for r in requirements if r.status == "PASS")
+        failed = sum(1 for r in requirements if r.status == "FAIL")
+        manual = sum(1 for r in requirements if r.status == "MANUAL")
+
+        return cls(
+            requirements=requirements,
+            total_count=len(requirements),
+            passed_count=passed,
+            failed_count=failed,
+            manual_count=manual,
+        )

mcp_server/prowler_mcp_server/prowler_app/tools/base.py

@@ -33,7 +33,7 @@ class BaseTool(ABC):
 
             async def search_security_findings(self, severity: list[str] = Field(...)):
                 # Implementation with access to self.api_client
-                response = await self.api_client.get("/api/v1/findings")
+                response = await self.api_client.get("/findings")
                 return response
     """
 

mcp_server/prowler_mcp_server/prowler_app/tools/compliance.py

@@ -0,0 +1,409 @@
+"""Compliance framework tools for Prowler App MCP Server.
+
+This module provides tools for viewing compliance status and requirement details
+across all cloud providers.
+"""
+
+from typing import Any
+
+from prowler_mcp_server.prowler_app.models.compliance import (
+    ComplianceFrameworksListResponse,
+    ComplianceRequirementAttributesListResponse,
+    ComplianceRequirementsListResponse,
+)
+from prowler_mcp_server.prowler_app.tools.base import BaseTool
+from pydantic import Field
+
+
+class ComplianceTools(BaseTool):
+    """Tools for compliance framework operations.
+
+    Provides tools for:
+    - get_compliance_overview: Get high-level compliance status across all frameworks
+    - get_compliance_framework_state_details: Get detailed requirement-level breakdown for a specific framework
+    """
+
+    async def _get_latest_scan_id_for_provider(self, provider_id: str) -> str:
+        """Get the latest completed scan_id for a given provider.
+
+        Args:
+            provider_id: Prowler's internal UUID for the provider
+
+        Returns:
+            The scan_id of the latest completed scan for the provider.
+
+        Raises:
+            ValueError: If no completed scans are found for the provider.
+        """
+        scan_params = {
+            "filter[provider]": provider_id,
+            "filter[state]": "completed",
+            "sort": "-inserted_at",
+            "page[size]": 1,
+            "page[number]": 1,
+        }
+        clean_scan_params = self.api_client.build_filter_params(scan_params)
+        scans_response = await self.api_client.get("/scans", params=clean_scan_params)
+
+        scans_data = scans_response.get("data", [])
+        if not scans_data:
+            raise ValueError(
+                f"No completed scans found for provider {provider_id}. "
+                "Run a scan first using prowler_app_trigger_scan."
+            )
+
+        scan_id = scans_data[0]["id"]
+        return scan_id
+
+    async def get_compliance_overview(
+        self,
+        scan_id: str | None = Field(
+            default=None,
+            description="UUID of a specific scan to get compliance data for. Required if provider_id is not specified. Use `prowler_app_list_scans` to find scan IDs.",
+        ),
+        provider_id: str | None = Field(
+            default=None,
+            description="Prowler's internal UUID (v4) for a specific provider. If provided without scan_id, the tool will automatically find the latest completed scan for this provider. Use `prowler_app_search_providers` tool to find provider IDs.",
+        ),
+    ) -> dict[str, Any]:
+        """Get high-level compliance overview across all frameworks for a specific scan.
+
+        This tool provides a HIGH-LEVEL OVERVIEW of compliance status across all frameworks.
+        Use this when you need to understand overall compliance posture before drilling into
+        specific framework details.
+
+        You have two options to specify the scan context:
+        1. Provide a specific scan_id to get compliance data for that scan.
+        2. Provide a provider_id to get compliance data from the latest completed scan for that provider.
+
+        The markdown report includes:
+
+        1. Summary Statistics:
+           - Total number of compliance frameworks evaluated
+           - Overall compliance metrics across all frameworks
+
+        2. Per-Framework Breakdown:
+           - Framework name, version, and compliance ID
+           - Requirements passed/failed/manual counts
+           - Pass percentage for quick assessment
+
+        Workflow:
+        1. Use this tool to get an overview of all compliance frameworks
+        2. Use prowler_app_get_compliance_framework_state_details with a specific compliance_id to see which requirements failed
+        """
+        if not scan_id and not provider_id:
+            return {
+                "error": "Either scan_id or provider_id must be provided. Use prowler_app_search_providers to find provider IDs or prowler_app_list_scans to find scan IDs."
+            }
+        elif scan_id and provider_id:
+            return {
+                "error": "Provide either scan_id or provider_id, not both. To get compliance data for a specific scan, use scan_id. To get data for the latest scan of a provider, use provider_id."
+            }
+        elif not scan_id and provider_id:
+            try:
+                scan_id = await self._get_latest_scan_id_for_provider(provider_id)
+            except ValueError as e:
+                return {"error": str(e)}
+
+        params: dict[str, Any] = {"filter[scan_id]": scan_id}
+
+        clean_params = self.api_client.build_filter_params(params)
+
+        # Get API response
+        api_response = await self.api_client.get(
+            "/compliance-overviews", params=clean_params
+        )
+        frameworks_response = ComplianceFrameworksListResponse.from_api_response(
+            api_response
+        )
+
+        # Build markdown report
+        frameworks = frameworks_response.frameworks
+        total_frameworks = frameworks_response.total_count
+
+        if total_frameworks == 0:
+            return {"report": "# Compliance Overview\n\nNo compliance frameworks found"}
+
+        # Calculate aggregate statistics
+        total_requirements = sum(f.total_requirements for f in frameworks)
+        total_passed = sum(f.requirements_passed for f in frameworks)
+        total_failed = sum(f.requirements_failed for f in frameworks)
+        total_manual = sum(f.requirements_manual for f in frameworks)
+        overall_pass_pct = (
+            round((total_passed / total_requirements) * 100, 1)
+            if total_requirements > 0
+            else 0
+        )
+
+        # Build report
+        report_lines = [
+            "# Compliance Overview",
+            "",
+            "## Summary Statistics",
+            f"- **Frameworks Evaluated**: {total_frameworks}",
+            f"- **Total Requirements**: {total_requirements:,}",
+            f"- **Passed**: {total_passed:,} ({overall_pass_pct}%)",
+            f"- **Failed**: {total_failed:,}",
+            f"- **Manual Review**: {total_manual:,}",
+            "",
+            "## Framework Breakdown",
+            "",
+        ]
+
+        # Sort frameworks by fail count (most failures first)
+        sorted_frameworks = sorted(
+            frameworks, key=lambda f: f.requirements_failed, reverse=True
+        )
+
+        for fw in sorted_frameworks:
+            status_indicator = "PASS" if fw.requirements_failed == 0 else "FAIL"
+
+            report_lines.append(f"### {fw.framework} {fw.version}")
+            report_lines.append(f"- **Compliance ID**: `{fw.compliance_id}`")
+            report_lines.append(f"- **Status**: {status_indicator}")
+            report_lines.append(
+                f"- **Requirements**: {fw.requirements_passed}/{fw.total_requirements} passed ({fw.pass_percentage}%)"
+            )
+            if fw.requirements_failed > 0:
+                report_lines.append(f"- **Failed**: {fw.requirements_failed}")
+            if fw.requirements_manual > 0:
+                report_lines.append(f"- **Manual Review**: {fw.requirements_manual}")
+            report_lines.append("")
+
+        return {"report": "\n".join(report_lines)}
+
+    async def _get_requirement_check_ids_mapping(
+        self, compliance_id: str
+    ) -> dict[str, list[str]]:
+        """Get mapping of requirement IDs to their associated check IDs.
+
+        Args:
+            compliance_id: The compliance framework ID.
+
+        Returns:
+            Dictionary mapping requirement ID to list of check IDs.
+        """
+        params: dict[str, Any] = {
+            "filter[compliance_id]": compliance_id,
+            "fields[compliance-requirements-attributes]": "id,attributes",
+        }
+
+        clean_params = self.api_client.build_filter_params(params)
+
+        api_response = await self.api_client.get(
+            "/compliance-overviews/attributes", params=clean_params
+        )
+        attributes_response = (
+            ComplianceRequirementAttributesListResponse.from_api_response(api_response)
+        )
+
+        # Build mapping: requirement_id -> [check_ids]
+        return {req.id: req.check_ids for req in attributes_response.requirements}
+
+    async def _get_failed_finding_ids_for_checks(
+        self,
+        check_ids: list[str],
+        scan_id: str,
+    ) -> list[str]:
+        """Get all failed finding IDs for a list of check IDs.
+
+        Args:
+            check_ids: List of Prowler check IDs.
+            scan_id: The scan ID to filter findings.
+
+        Returns:
+            List of all finding IDs with FAIL status.
+        """
+        if not check_ids:
+            return []
+
+        all_finding_ids: list[str] = []
+        page_number = 1
+        page_size = 100
+
+        while True:
+            # Query findings endpoint with check_id filter and FAIL status
+            params: dict[str, Any] = {
+                "filter[scan]": scan_id,
+                "filter[check_id__in]": ",".join(check_ids),
+                "filter[status]": "FAIL",
+                "fields[findings]": "uid",
+                "page[size]": page_size,
+                "page[number]": page_number,
+            }
+
+            clean_params = self.api_client.build_filter_params(params)
+
+            api_response = await self.api_client.get("/findings", params=clean_params)
+
+            findings = api_response.get("data", [])
+            if not findings:
+                break
+
+            all_finding_ids.extend([f["id"] for f in findings])
+
+            # Check if we've reached the last page
+            if len(findings) < page_size:
+                break
+
+            page_number += 1
+
+        return all_finding_ids
+
+    async def get_compliance_framework_state_details(
+        self,
+        compliance_id: str = Field(
+            description="Compliance framework ID to get details for (e.g., 'cis_1.5_aws', 'pci_dss_v4.0_aws'). You can get compliance IDs from prowler_app_get_compliance_overview or consulting Prowler Hub/Prowler Documentation that you can also find in form of tools in this MCP Server",
+        ),
+        scan_id: str | None = Field(
+            default=None,
+            description="UUID of a specific scan to get compliance data for. Required if provider_id is not specified.",
+        ),
+        provider_id: str | None = Field(
+            default=None,
+            description="Prowler's internal UUID (v4) for a specific provider. If provided without scan_id, the tool will automatically find the latest completed scan for this provider. Use `prowler_app_search_providers` tool to find provider IDs.",
+        ),
+    ) -> dict[str, Any]:
+        """Get detailed requirement-level breakdown for a specific compliance framework.
+
+        IMPORTANT: This tool returns DETAILED requirement information for a single compliance framework,
+        focusing on FAILED requirements and their associated FAILED finding IDs.
+        Use this after prowler_app_get_compliance_overview to drill down into specific frameworks.
+
+        The markdown report includes:
+
+        1. Framework Summary:
+           - Compliance ID and scan ID used
+           - Overall pass/fail/manual counts
+
+        2. Failed Requirements Breakdown:
+           - Each failed requirement's ID and description
+           - Associated failed finding IDs for each failed requirement
+           - Use prowler_app_get_finding_details with these finding IDs for more details and remediation guidance
+
+        Default behavior:
+        - Requires either scan_id OR provider_id
+        - With provider_id (no scan_id): Automatically finds the latest completed scan for that provider
+        - With scan_id: Uses that specific scan's compliance data
+        - Only shows failed requirements with their associated failed finding IDs
+
+        Workflow:
+        1. Use prowler_app_get_compliance_overview to identify frameworks with failures
+        2. Use this tool with the compliance_id to see failed requirements and their finding IDs
+        3. Use prowler_app_get_finding_details with the finding IDs to get remediation guidance
+        """
+        # Validate that either scan_id or provider_id is provided
+        if not scan_id and not provider_id:
+            return {
+                "error": "Either scan_id or provider_id must be provided. Use prowler_app_search_providers to find provider IDs or prowler_app_list_scans to find scan IDs."
+            }
+
+        # Resolve provider_id to latest scan_id if needed
+        resolved_scan_id = scan_id
+        if not scan_id and provider_id:
+            try:
+                resolved_scan_id = await self._get_latest_scan_id_for_provider(
+                    provider_id
+                )
+            except ValueError as e:
+                return {"error": str(e)}
+
+        # Build params for requirements endpoint
+        params: dict[str, Any] = {
+            "filter[scan_id]": resolved_scan_id,
+            "filter[compliance_id]": compliance_id,
+        }
+
+        params["fields[compliance-requirements-details]"] = "id,description,status"
+
+        clean_params = self.api_client.build_filter_params(params)
+
+        # Get API response
+        api_response = await self.api_client.get(
+            "/compliance-overviews/requirements", params=clean_params
+        )
+        requirements_response = ComplianceRequirementsListResponse.from_api_response(
+            api_response
+        )
+
+        requirements = requirements_response.requirements
+
+        if not requirements:
+            return {
+                "report": f"# Compliance Framework Details\n\n**Compliance ID**: `{compliance_id}`\n\nNo requirements found for this compliance framework and scan combination."
+            }
+
+        # Get failed requirements
+        failed_reqs = [r for r in requirements if r.status == "FAIL"]
+
+        # Get requirement -> check_ids mapping from attributes endpoint
+        requirement_check_mapping: dict[str, list[str]] = {}
+        if failed_reqs:
+            requirement_check_mapping = await self._get_requirement_check_ids_mapping(
+                compliance_id
+            )
+
+        # For each failed requirement, get the failed finding IDs
+        failed_req_findings: dict[str, list[str]] = {}
+        for req in failed_reqs:
+            check_ids = requirement_check_mapping.get(req.id, [])
+            if check_ids:
+                finding_ids = await self._get_failed_finding_ids_for_checks(
+                    check_ids, resolved_scan_id
+                )
+                failed_req_findings[req.id] = finding_ids
+
+        # Calculate counts
+        total_count = len(requirements)
+        passed_count = sum(1 for r in requirements if r.status == "PASS")
+        failed_count = len(failed_reqs)
+        manual_count = sum(1 for r in requirements if r.status == "MANUAL")
+
+        # Build markdown report
+        pass_pct = (
+            round((passed_count / total_count) * 100, 1) if total_count > 0 else 0
+        )
+
+        report_lines = [
+            "# Compliance Framework Details",
+            "",
+            f"**Compliance ID**: `{compliance_id}`",
+            f"**Scan ID**: `{resolved_scan_id}`",
+            "",
+            "## Summary",
+            f"- **Total Requirements**: {total_count}",
+            f"- **Passed**: {passed_count} ({pass_pct}%)",
+            f"- **Failed**: {failed_count}",
+            f"- **Manual Review**: {manual_count}",
+            "",
+        ]
+
+        # Show failed requirements with their finding IDs (most actionable)
+        if failed_reqs:
+            report_lines.append("## Failed Requirements")
+            report_lines.append("")
+            for req in failed_reqs:
+                report_lines.append(f"### {req.id}")
+                report_lines.append(f"**Description**: {req.description}")
+                finding_ids = failed_req_findings.get(req.id, [])
+                if finding_ids:
+                    report_lines.append(f"**Failed Finding IDs** ({len(finding_ids)}):")
+                    for fid in finding_ids:
+                        report_lines.append(f"  - `{fid}`")
+                else:
+                    report_lines.append("**Failed Finding IDs**: None found")
+                report_lines.append("")
+            report_lines.append(
+                "*Use `prowler_app_get_finding_details` with these finding IDs to get remediation guidance.*"
+            )
+            report_lines.append("")
+
+        if manual_count > 0:
+            manual_reqs = [r for r in requirements if r.status == "MANUAL"]
+            report_lines.append("## Requirements Requiring Manual Review")
+            report_lines.append("")
+            for req in manual_reqs:
+                report_lines.append(f"- **{req.id}**: {req.description}")
+            report_lines.append("")
+
+        return {"report": "\n".join(report_lines)}

mcp_server/prowler_mcp_server/prowler_app/tools/findings.py

@@ -6,13 +6,14 @@ across all cloud providers.
 
 from typing import Any, Literal
 
+from pydantic import Field
+
 from prowler_mcp_server.prowler_app.models.findings import (
     DetailedFinding,
     FindingsListResponse,
     FindingsOverview,
 )
 from prowler_mcp_server.prowler_app.tools.base import BaseTool
-from pydantic import Field
 
 
 class FindingsTools(BaseTool):
@@ -122,11 +123,11 @@ class FindingsTools(BaseTool):
 
         if date_range is None:
             # No dates provided - use latest findings endpoint
-            endpoint = "/api/v1/findings/latest"
+            endpoint = "/findings/latest"
             params = {}
         else:
             # Dates provided - use historical findings endpoint
-            endpoint = "/api/v1/findings"
+            endpoint = "/findings"
             params = {
                 "filter[inserted_at__gte]": date_range[0],
                 "filter[inserted_at__lte]": date_range[1],
@@ -228,7 +229,7 @@ class FindingsTools(BaseTool):
 
         # Get API response and transform to detailed format
         api_response = await self.api_client.get(
-            f"/api/v1/findings/{finding_id}", params=params
+            f"/findings/{finding_id}", params=params
         )
         detailed_finding = DetailedFinding.from_api_response(
             api_response.get("data", {})
@@ -281,7 +282,7 @@ class FindingsTools(BaseTool):
 
         # Get API response and transform to simplified format
         api_response = await self.api_client.get(
-            "/api/v1/overviews/findings", params=clean_params
+            "/overviews/findings", params=clean_params
         )
         overview = FindingsOverview.from_api_response(api_response)
 

mcp_server/prowler_mcp_server/prowler_app/tools/muting.py

@@ -8,13 +8,14 @@ This module provides tools for managing finding muting in Prowler, including:
 import json
 from typing import Any
 
+from pydantic import Field
+
 from prowler_mcp_server.prowler_app.models.muting import (
     DetailedMuteRule,
     MutelistResponse,
     MuteRulesListResponse,
 )
 from prowler_mcp_server.prowler_app.tools.base import BaseTool
-from pydantic import Field
 
 
 class MutingTools(BaseTool):
@@ -53,9 +54,7 @@ class MutingTools(BaseTool):
         }
 
         clean_params = self.api_client.build_filter_params(params)
-        api_response = await self.api_client.get(
-            "/api/v1/processors", params=clean_params
-        )
+        api_response = await self.api_client.get("/processors", params=clean_params)
 
         data = api_response.get("data", [])
 
@@ -145,7 +144,7 @@ Structure:
             }
 
             api_response = await self.api_client.post(
-                "/api/v1/processors", json_data=create_body
+                "/processors", json_data=create_body
             )
             mutelist = MutelistResponse.from_api_response(api_response.get("data", {}))
             return mutelist.model_dump()
@@ -163,7 +162,7 @@ Structure:
             }
 
             api_response = await self.api_client.patch(
-                f"/api/v1/processors/{existing_mutelist['id']}", json_data=update_body
+                f"/processors/{existing_mutelist['id']}", json_data=update_body
             )
             mutelist = MutelistResponse.from_api_response(api_response.get("data", {}))
             return mutelist.model_dump()
@@ -194,7 +193,7 @@ Structure:
 
         # Delete the mutelist
         mutelist_id = existing_mutelist["id"]
-        await self.api_client.delete(f"/api/v1/processors/{mutelist_id}")
+        await self.api_client.delete(f"/processors/{mutelist_id}")
 
         return {
             "success": True,
@@ -276,9 +275,7 @@ Structure:
             params["filter[search]"] = search
 
         clean_params = self.api_client.build_filter_params(params)
-        api_response = await self.api_client.get(
-            "/api/v1/mute-rules", params=clean_params
-        )
+        api_response = await self.api_client.get("/mute-rules", params=clean_params)
 
         simplified_response = MuteRulesListResponse.from_api_response(api_response)
         return simplified_response.model_dump()
@@ -311,7 +308,7 @@ Structure:
         }
 
         api_response = await self.api_client.get(
-            f"/api/v1/mute-rules/{rule_id}", params=params
+            f"/mute-rules/{rule_id}", params=params
         )
 
         detailed_rule = DetailedMuteRule.from_api_response(api_response.get("data", {}))
@@ -363,9 +360,7 @@ Structure:
             }
         }
 
-        api_response = await self.api_client.post(
-            "/api/v1/mute-rules", json_data=create_body
-        )
+        api_response = await self.api_client.post("/mute-rules", json_data=create_body)
 
         detailed_rule = DetailedMuteRule.from_api_response(api_response.get("data", {}))
         return detailed_rule.model_dump()
@@ -432,10 +427,9 @@ Structure:
         }
 
         api_response = await self.api_client.patch(
-            f"/api/v1/mute-rules/{rule_id}", json_data=update_body
+            f"/mute-rules/{rule_id}", json_data=update_body
         )
 
-        self.logger.info(f"API response: {api_response}")
         detailed_rule = DetailedMuteRule.from_api_response(api_response.get("data", {}))
         return detailed_rule.model_dump()
 
@@ -463,7 +457,7 @@ Structure:
         """
         self.logger.info(f"Deleting mute rule {rule_id}...")
 
-        result = await self.api_client.delete(f"/api/v1/mute-rules/{rule_id}")
+        result = await self.api_client.delete(f"/mute-rules/{rule_id}")
 
         if result.get("success"):
             return {

mcp_server/prowler_mcp_server/prowler_app/tools/providers.py

@@ -6,12 +6,13 @@ including searching, connecting, and deleting providers.
 
 from typing import Any
 
+from pydantic import Field
+
 from prowler_mcp_server.prowler_app.models.providers import (
     ProviderConnectionStatus,
     ProvidersListResponse,
 )
 from prowler_mcp_server.prowler_app.tools.base import BaseTool
-from pydantic import Field
 
 
 class ProvidersTools(BaseTool):
@@ -100,9 +101,7 @@ class ProvidersTools(BaseTool):
 
         clean_params = self.api_client.build_filter_params(params)
 
-        api_response = await self.api_client.get(
-            "/api/v1/providers", params=clean_params
-        )
+        api_response = await self.api_client.get("/providers", params=clean_params)
         simplified_response = ProvidersListResponse.from_api_response(api_response)
 
         # Fetch secret_type for each provider that has a secret
@@ -306,9 +305,7 @@ class ProvidersTools(BaseTool):
         self.logger.info(f"Deleting provider {provider_id}...")
         try:
             # Initiate the deletion task
-            task_response = await self.api_client.delete(
-                f"/api/v1/providers/{provider_id}"
-            )
+            task_response = await self.api_client.delete(f"/providers/{provider_id}")
             task_id = task_response.get("data", {}).get("id")
 
             # Poll until task completes (with 60 second timeout)
@@ -345,7 +342,7 @@ class ProvidersTools(BaseTool):
         """
         self.logger.info(f"Checking if provider {provider_uid} exists...")
         response = await self.api_client.get(
-            "/api/v1/providers", params={"filter[uid]": provider_uid}
+            "/providers", params={"filter[uid]": provider_uid}
         )
         providers = response.get("data", [])
 
@@ -391,7 +388,7 @@ class ProvidersTools(BaseTool):
         if alias:
             provider_body["data"]["attributes"]["alias"] = alias
 
-        await self.api_client.post("/api/v1/providers", json_data=provider_body)
+        await self.api_client.post("/providers", json_data=provider_body)
 
         provider_id = await self._check_provider_exists(provider_uid)
         if provider_id is None:
@@ -418,7 +415,7 @@ class ProvidersTools(BaseTool):
             }
         }
         result = await self.api_client.patch(
-            f"/api/v1/providers/{prowler_provider_id}", json_data=update_body
+            f"/providers/{prowler_provider_id}", json_data=update_body
         )
         if result.get("data", {}).get("attributes", {}).get("alias") != alias:
             raise Exception(f"Provider {prowler_provider_id} alias update failed")
@@ -450,7 +447,7 @@ class ProvidersTools(BaseTool):
         """
         try:
             response = await self.api_client.get(
-                "/api/v1/providers/secrets",
+                "/providers/secrets",
                 params={"filter[provider]": prowler_provider_id},
             )
             secrets = response.get("data", [])
@@ -481,7 +478,7 @@ class ProvidersTools(BaseTool):
         """
         try:
             response = await self.api_client.get(
-                f"/api/v1/providers/secrets/{secret_id}",
+                f"/providers/secrets/{secret_id}",
                 params={"fields[provider-secrets]": "secret_type"},
             )
             secret_type = (
@@ -536,7 +533,7 @@ class ProvidersTools(BaseTool):
             }
             try:
                 response = await self.api_client.patch(
-                    f"/api/v1/providers/secrets/{existing_secret_id}",
+                    f"/providers/secrets/{existing_secret_id}",
                     json_data=update_body,
                 )
                 self.logger.info("Credentials updated successfully")
@@ -567,7 +564,7 @@ class ProvidersTools(BaseTool):
 
             try:
                 response = await self.api_client.post(
-                    "/api/v1/providers/secrets", json_data=secret_body
+                    "/providers/secrets", json_data=secret_body
                 )
                 self.logger.info("Credentials added successfully")
                 return response
@@ -588,7 +585,7 @@ class ProvidersTools(BaseTool):
         try:
             # Initiate the connection test task
             task_response = await self.api_client.post(
-                f"/api/v1/providers/{prowler_provider_id}/connection", json_data={}
+                f"/providers/{prowler_provider_id}/connection", json_data={}
             )
             task_id = task_response.get("data", {}).get("id")
 
@@ -619,5 +616,5 @@ class ProvidersTools(BaseTool):
             Provider data dictionary
         """
         return await self.api_client.get(
-            f"/api/v1/providers/{prowler_provider_id}",
+            f"/providers/{prowler_provider_id}",
         )

mcp_server/prowler_mcp_server/prowler_app/tools/resources.py

@@ -6,13 +6,14 @@ across all providers.
 
 from typing import Any
 
+from pydantic import Field
+
 from prowler_mcp_server.prowler_app.models.resources import (
     DetailedResource,
     ResourcesListResponse,
     ResourcesMetadataResponse,
 )
 from prowler_mcp_server.prowler_app.tools.base import BaseTool
-from pydantic import Field
 
 
 class ResourcesTools(BaseTool):
@@ -121,11 +122,11 @@ class ResourcesTools(BaseTool):
 
         if date_range is None:
             # No dates provided - use latest resources endpoint
-            endpoint = "/api/v1/resources/latest"
+            endpoint = "/resources/latest"
             params = {}
         else:
             # Dates provided - use historical resources endpoint
-            endpoint = "/api/v1/resources"
+            endpoint = "/resources"
             params = {
                 "filter[updated_at__gte]": date_range[0],
                 "filter[updated_at__lte]": date_range[1],
@@ -206,9 +207,8 @@ class ResourcesTools(BaseTool):
 
         # Get API response and transform to detailed format
         api_response = await self.api_client.get(
-            f"/api/v1/resources/{resource_id}", params=params
+            f"/resources/{resource_id}", params=params
         )
-        self.logger.info(f"API response: {api_response}")
         detailed_resource = DetailedResource.from_api_response(
             api_response.get("data", {})
         )
@@ -265,13 +265,13 @@ class ResourcesTools(BaseTool):
 
         if date_range is None:
             # No dates provided - use latest metadata endpoint
-            metadata_endpoint = "/api/v1/resources/metadata/latest"
-            list_endpoint = "/api/v1/resources/latest"
+            metadata_endpoint = "/resources/metadata/latest"
+            list_endpoint = "/resources/latest"
             params = {}
         else:
             # Dates provided - use historical endpoints
-            metadata_endpoint = "/api/v1/resources/metadata"
-            list_endpoint = "/api/v1/resources"
+            metadata_endpoint = "/resources/metadata"
+            list_endpoint = "/resources"
             params = {
                 "filter[updated_at__gte]": date_range[0],
                 "filter[updated_at__lte]": date_range[1],

mcp_server/prowler_mcp_server/prowler_app/tools/scans.py

@@ -5,6 +5,8 @@ This module provides tools for managing and monitoring Prowler security scans.
 
 from typing import Any, Literal
 
+from pydantic import Field
+
 from prowler_mcp_server.prowler_app.models.scans import (
     DetailedScan,
     ScanCreationResult,
@@ -12,7 +14,6 @@ from prowler_mcp_server.prowler_app.models.scans import (
     ScheduleCreationResult,
 )
 from prowler_mcp_server.prowler_app.tools.base import BaseTool
-from pydantic import Field
 
 
 class ScansTools(BaseTool):
@@ -119,7 +120,7 @@ class ScansTools(BaseTool):
 
         clean_params = self.api_client.build_filter_params(params)
 
-        api_response = await self.api_client.get("/api/v1/scans", params=clean_params)
+        api_response = await self.api_client.get("/scans", params=clean_params)
         simplified_response = ScansListResponse.from_api_response(api_response)
 
         return simplified_response.model_dump()
@@ -163,9 +164,7 @@ class ScansTools(BaseTool):
             "fields[scans]": "name,trigger,state,progress,duration,unique_resource_count,started_at,completed_at,scheduled_at,next_scan_at,inserted_at"
         }
 
-        api_response = await self.api_client.get(
-            f"/api/v1/scans/{scan_id}", params=params
-        )
+        api_response = await self.api_client.get(f"/scans/{scan_id}", params=params)
         detailed_scan = DetailedScan.from_api_response(api_response["data"])
 
         return detailed_scan.model_dump()
@@ -213,9 +212,7 @@ class ScansTools(BaseTool):
 
             # Create scan (returns Task)
             self.logger.info(f"Creating scan for provider {provider_id}")
-            task_response = await self.api_client.post(
-                "/api/v1/scans", json_data=request_data
-            )
+            task_response = await self.api_client.post("/scans", json_data=request_data)
 
             scan_id = (
                 task_response.get("data", {})
@@ -228,7 +225,7 @@ class ScansTools(BaseTool):
                 raise Exception("No scan_id returned from scan creation")
 
             self.logger.info(f"Scan created successfully: {scan_id}")
-            scan_response = await self.api_client.get(f"/api/v1/scans/{scan_id}")
+            scan_response = await self.api_client.get(f"/scans/{scan_id}")
             scan_info = DetailedScan.from_api_response(scan_response["data"])
 
             return ScanCreationResult(
@@ -273,7 +270,7 @@ class ScansTools(BaseTool):
         """
         self.logger.info(f"Creating daily schedule for provider {provider_id}")
         task_response = await self.api_client.post(
-            "/api/v1/schedules/daily",
+            "/schedules/daily",
             json_data={
                 "data": {
                     "type": "daily-schedules",
@@ -316,7 +313,7 @@ class ScansTools(BaseTool):
         2. Use this tool with the scan 'id' and new name
         """
         api_response = await self.api_client.patch(
-            f"/api/v1/scans/{scan_id}",
+            f"/scans/{scan_id}",
             json_data={
                 "data": {
                     "type": "scans",

mcp_server/prowler_mcp_server/prowler_app/utils/api_client.py

@@ -228,7 +228,7 @@ class ProwlerAPIClient(metaclass=SingletonMeta):
                 )
 
             # Fetch current task state
-            response = await self.get(f"/api/v1/tasks/{task_id}")
+            response = await self.get(f"/tasks/{task_id}")
             task_data = response.get("data", {})
             task_attrs = task_data.get("attributes", {})
             state = task_attrs.get("state")

mcp_server/prowler_mcp_server/prowler_app/utils/auth.py

@@ -15,7 +15,7 @@ class ProwlerAppAuth:
     def __init__(
         self,
         mode: str = os.getenv("PROWLER_MCP_TRANSPORT_MODE", "stdio"),
-        base_url: str = os.getenv("PROWLER_API_BASE_URL", "https://api.prowler.com"),
+        base_url: str = os.getenv("API_BASE_URL", "https://api.prowler.com/api/v1"),
     ):
         self.base_url = base_url.rstrip("/")
         logger.info(f"Using Prowler App API base URL: {self.base_url}")

mcp_server/prowler_mcp_server/prowler_documentation/search_engine.py

@@ -1,5 +1,3 @@
-from typing import List, Optional
-
 import httpx
 from prowler_mcp_server import __version__
 from pydantic import BaseModel, Field
@@ -11,7 +9,7 @@ class SearchResult(BaseModel):
     path: str = Field(description="Document path")
     title: str = Field(description="Document title")
     url: str = Field(description="Documentation URL")
-    highlights: List[str] = Field(
+    highlights: list[str] = Field(
         description="Highlighted content snippets showing query matches with <mark><b> tags",
         default_factory=list,
     )
@@ -54,7 +52,7 @@ class ProwlerDocsSearchEngine:
             },
         )
 
-    def search(self, query: str, page_size: int = 5) -> List[SearchResult]:
+    def search(self, query: str, page_size: int = 5) -> list[SearchResult]:
         """
         Search documentation using Mintlify API.
 
@@ -63,7 +61,7 @@ class ProwlerDocsSearchEngine:
             page_size: Maximum number of results to return
 
         Returns:
-            List of search results
+            list of search results
         """
         try:
             # Construct request body
@@ -139,7 +137,7 @@ class ProwlerDocsSearchEngine:
             print(f"Search error: {e}")
             return []
 
-    def get_document(self, doc_path: str) -> Optional[str]:
+    def get_document(self, doc_path: str) -> str | None:
         """
         Get full document content from Mintlify documentation.
 

mcp_server/prowler_mcp_server/prowler_documentation/server.py

@@ -1,6 +1,8 @@
-from typing import Any, List
+from typing import Any
 
 from fastmcp import FastMCP
+from pydantic import Field
+
 from prowler_mcp_server.prowler_documentation.search_engine import (
     ProwlerDocsSearchEngine,
 )
@@ -12,46 +14,44 @@ prowler_docs_search_engine = ProwlerDocsSearchEngine()
 
 @docs_mcp_server.tool()
 def search(
-    query: str,
-    page_size: int = 5,
-) -> List[dict[str, Any]]:
-    """
-    Search in Prowler documentation.
+    term: str = Field(description="The term to search for in the documentation"),
+    page_size: int = Field(
+        5,
+        description="Number of top results to return to return. It must be between 1 and 20.",
+        gt=1,
+        lt=20,
+    ),
+) -> list[dict[str, Any]]:
+    """Search in Prowler documentation.
 
     This tool searches through the official Prowler documentation
-    to find relevant information about security checks, cloud providers,
-    compliance frameworks, and usage instructions.
+    to find relevant information about everything related to Prowler.
 
     Uses fulltext search to find the most relevant documentation pages
     based on your query.
 
-    Args:
-        query: The search query
-        page_size: Number of top results to return (default: 5)
-
     Returns:
         List of search results with highlights showing matched terms (in <mark><b> tags)
     """
-    return prowler_docs_search_engine.search(query, page_size)
+    return prowler_docs_search_engine.search(term, page_size)  # type: ignore In the hint we cannot put SearchResult type because JSON API MCP Generator cannot handle Pydantic models yet
 
 
 @docs_mcp_server.tool()
 def get_document(
-    doc_path: str,
-) -> str:
-    """
-    Retrieve the full content of a Prowler documentation file.
+    doc_path: str = Field(
+        description="Path to the documentation file to retrieve. It is the same as the 'path' field of the search results. Use `prowler_docs_search` to find the path first."
+    ),
+) -> dict[str, str]:
+    """Retrieve the full content of a Prowler documentation file.
 
     Use this after searching to get the complete content of a specific
     documentation file.
 
-    Args:
-        doc_path: Path to the documentation file. It is the same as the "path" field of the search results.
-
     Returns:
-        Full content of the documentation file
+        Full content of the documentation file in markdown format.
     """
-    content = prowler_docs_search_engine.get_document(doc_path)
+    content: str | None = prowler_docs_search_engine.get_document(doc_path)
     if content is None:
-        raise ValueError(f"Document not found: {doc_path}")
-    return content
+        return {"error": f"Document '{doc_path}' not found."}
+    else:
+        return {"content": content}

mcp_server/prowler_mcp_server/prowler_hub/server.py

@@ -4,10 +4,10 @@ Prowler Hub MCP module
 Provides access to Prowler Hub API for security checks and compliance frameworks.
 """
 
-from typing import Any, Optional
-
 import httpx
 from fastmcp import FastMCP
+from pydantic import Field
+
 from prowler_mcp_server import __version__
 
 # Initialize FastMCP for Prowler Hub
@@ -55,109 +55,90 @@ def github_check_path(provider_id: str, check_id: str, suffix: str) -> str:
     return f"{GITHUB_RAW_BASE}/{provider_id}/services/{service_id}/{check_id}/{check_id}{suffix}"
 
 
-@hub_mcp_server.tool()
-async def get_check_filters() -> dict[str, Any]:
-    """
-    Get available values for filtering for tool `get_checks`. Recommended to use before calling `get_checks` to get the available values for the filters.
-
-    Returns:
-        Available filter options including providers, types, services, severities,
-        categories, and compliance frameworks with their respective counts
-    """
-    try:
-        response = prowler_hub_client.get("/check/filters")
-        response.raise_for_status()
-        filters = response.json()
-
-        return {"filters": filters}
-    except httpx.HTTPStatusError as e:
-        return {
-            "error": f"HTTP error {e.response.status_code}: {e.response.text}",
-        }
-    except Exception as e:
-        return {"error": str(e)}
-
-
 # Security Check Tools
 @hub_mcp_server.tool()
-async def get_checks(
-    providers: Optional[str] = None,
-    types: Optional[str] = None,
-    services: Optional[str] = None,
-    severities: Optional[str] = None,
-    categories: Optional[str] = None,
-    compliances: Optional[str] = None,
-    ids: Optional[str] = None,
-    fields: Optional[str] = "id,service,severity,title,description,risk",
-) -> dict[str, Any]:
-    """
-    List security Prowler Checks. The list can be filtered by the parameters defined for the tool.
-    It is recommended to use the tool `get_check_filters` to get the available values for the filters.
-    A not filtered request will return more than 1000 checks, so it is recommended to use the filters.
+async def list_checks(
+    providers: list[str] = Field(
+        default=[],
+        description="Filter by Prowler provider IDs. Example: ['aws', 'azure']. Use `prowler_hub_list_providers` to get available provider IDs.",
+    ),
+    services: list[str] = Field(
+        default=[],
+        description="Filter by provider services. Example: ['s3', 'ec2', 'keyvault']. Use `prowler_hub_get_provider_services` to get available services for a provider.",
+    ),
+    severities: list[str] = Field(
+        default=[],
+        description="Filter by severity levels. Example: ['high', 'critical']. Available: 'low', 'medium', 'high', 'critical'.",
+    ),
+    categories: list[str] = Field(
+        default=[],
+        description="Filter by security categories. Example: ['encryption', 'internet-exposed'].",
+    ),
+    compliances: list[str] = Field(
+        default=[],
+        description="Filter by compliance framework IDs. Example: ['cis_4.0_aws', 'ens_rd2022_azure']. Use `prowler_hub_list_compliances` to get available compliance IDs.",
+    ),
+) -> dict:
+    """List security Prowler Checks with filtering capabilities.
 
-    Args:
-        providers: Filter by Prowler provider IDs. Example: "aws,azure". Use the tool `list_providers` to get the available providers IDs.
-        types: Filter by check types.
-        services: Filter by provider services IDs. Example: "s3,keyvault". Use the tool `list_providers` to get the available services IDs in a provider.
-        severities: Filter by severity levels. Example: "medium,high". Available values are "low", "medium", "high", "critical".
-        categories: Filter by categories. Example: "cluster-security,encryption".
-        compliances: Filter by compliance framework IDs. Example: "cis_4.0_aws,ens_rd2022_azure".
-        ids: Filter by specific check IDs. Example: "s3_bucket_level_public_access_block".
-        fields: Specify which fields from checks metadata to return (id is always included). Example: "id,title,description,risk".
-            Available values are "id", "title", "description", "provider", "type", "service", "subservice", "severity", "risk", "reference", "remediation", "services_required", "aws_arn_template", "notes", "categories", "default_value", "resource_type", "related_url", "depends_on", "related_to", "fixer".
-            The default parameters are "id,title,description".
-            If null, all fields will be returned.
+    IMPORTANT: This tool returns LIGHTWEIGHT check data. Use this for fast browsing and filtering.
+    For complete details including risk, remediation guidance, and categories use `prowler_hub_get_check_details`.
+
+    IMPORTANT: An unfiltered request returns 1000+ checks. Use filters to narrow results.
 
     Returns:
-        List of security checks matching the filters. The structure is as follows:
         {
             "count": N,
             "checks": [
-                {"id": "check_id_1", "title": "check_title_1", "description": "check_description_1", ...},
-                {"id": "check_id_2", "title": "check_title_2", "description": "check_description_2", ...},
-                {"id": "check_id_3", "title": "check_title_3", "description": "check_description_3", ...},
+                {
+                    "id": "check_id",
+                    "provider": "provider_id",
+                    "title": "Human-readable check title",
+                    "severity": "critical|high|medium|low",
+                },
                 ...
             ]
         }
+
+    Useful Example Workflow:
+    1. Use `prowler_hub_list_providers` to see available Prowler providers
+    2. Use `prowler_hub_get_provider_services` to see services for a provider
+    3. Use this tool with filters to find relevant checks
+    4. Use `prowler_hub_get_check_details` to get complete information for a specific check
     """
-    params: dict[str, str] = {}
+    # Lightweight fields for listing
+    lightweight_fields = "id,title,severity,provider"
+
+    params: dict[str, str] = {"fields": lightweight_fields}
 
     if providers:
-        params["providers"] = providers
-    if types:
-        params["types"] = types
+        params["providers"] = ",".join(providers)
     if services:
-        params["services"] = services
+        params["services"] = ",".join(services)
     if severities:
-        params["severities"] = severities
+        params["severities"] = ",".join(severities)
     if categories:
-        params["categories"] = categories
+        params["categories"] = ",".join(categories)
     if compliances:
-        params["compliances"] = compliances
-    if ids:
-        params["ids"] = ids
-    if fields:
-        params["fields"] = fields
+        params["compliances"] = ",".join(compliances)
 
     try:
         response = prowler_hub_client.get("/check", params=params)
         response.raise_for_status()
         checks = response.json()
 
-        checks_dict = {}
+        # Return checks as a lightweight list
+        checks_list = []
         for check in checks:
-            check_data = {}
-            # Always include the id field as it's mandatory for the response structure
-            if "id" in check:
-                check_data["id"] = check["id"]
+            check_data = {
+                "id": check["id"],
+                "provider": check["provider"],
+                "title": check["title"],
+                "severity": check["severity"],
+            }
+            checks_list.append(check_data)
 
-            # Include other requested fields
-            for field in fields.split(","):
-                if field != "id" and field in check:  # Skip id since it's already added
-                    check_data[field] = check[field]
-            checks_dict[check["id"]] = check_data
-
-        return {"count": len(checks), "checks": checks_dict}
+        return {"count": len(checks), "checks": checks_list}
     except httpx.HTTPStatusError as e:
         return {
             "error": f"HTTP error {e.response.status_code}: {e.response.text}",
@@ -167,60 +148,220 @@ async def get_checks(
 
 
 @hub_mcp_server.tool()
-async def get_check_raw_metadata(
-    provider_id: str,
-    check_id: str,
-) -> dict[str, Any]:
-    """
-    Fetch the raw check metadata JSON, this is a low level version of the tool `get_checks`.
-    It is recommended to use the tool `get_checks` filtering about the `ids` parameter instead of using this tool.
+async def semantic_search_checks(
+    term: str = Field(
+        description="Search term. Examples: 'public access', 'encryption', 'MFA', 'logging'.",
+    ),
+) -> dict:
+    """Search for security checks using free-text search across all metadata.
 
-    Args:
-        provider_id: Prowler provider ID (e.g., "aws", "azure").
-        check_id: Prowler check ID (folder and base filename).
+    IMPORTANT: This tool returns LIGHTWEIGHT check data. Use this for discovering checks by topic.
+    For complete details including risk, remediation guidance, and categories use `prowler_hub_get_check_details`.
+
+    Searches across check titles, descriptions, risk statements, remediation guidance,
+    and other text fields. Use this when you don't know the exact check ID or want to
+    explore checks related to a topic.
 
     Returns:
-        Raw metadata JSON as stored in Prowler.
-    """
-    if provider_id and check_id:
-        url = github_check_path(provider_id, check_id, ".metadata.json")
-        try:
-            resp = github_raw_client.get(url)
-            resp.raise_for_status()
-            return resp.json()
-        except httpx.HTTPStatusError as e:
-            if e.response.status_code == 404:
-                return {
-                    "error": f"Check {check_id} not found in Prowler",
-                }
-            else:
-                return {
-                    "error": f"HTTP error {e.response.status_code}: {e.response.text}",
-                }
-        except Exception as e:
-            return {
-                "error": f"Error fetching check {check_id} from Prowler: {str(e)}",
-            }
-    else:
-        return {
-            "error": "Provider ID and check ID are required",
+        {
+            "count": N,
+            "checks": [
+                {
+                    "id": "check_id",
+                    "provider": "provider_id",
+                    "title": "Human-readable check title",
+                    "severity": "critical|high|medium|low",
+                },
+                ...
+            ]
         }
 
+    Useful Example Workflow:
+    1. Use this tool to search for checks by keyword or topic
+    2. Use `prowler_hub_list_checks` with filters for more targeted browsing
+    3. Use `prowler_hub_get_check_details` to get complete information for a specific check
+    """
+    try:
+        response = prowler_hub_client.get("/check/search", params={"term": term})
+        response.raise_for_status()
+        checks = response.json()
+
+        # Return checks as a lightweight list
+        checks_list = []
+        for check in checks:
+            check_data = {
+                "id": check["id"],
+                "provider": check["provider"],
+                "title": check["title"],
+                "severity": check["severity"],
+            }
+            checks_list.append(check_data)
+
+        return {"count": len(checks), "checks": checks_list}
+    except httpx.HTTPStatusError as e:
+        return {
+            "error": f"HTTP error {e.response.status_code}: {e.response.text}",
+        }
+    except Exception as e:
+        return {"error": str(e)}
+
+
+@hub_mcp_server.tool()
+async def get_check_details(
+    check_id: str = Field(
+        description="The check ID to retrieve details for. Example: 's3_bucket_level_public_access_block'"
+    ),
+) -> dict:
+    """Retrieve comprehensive details about a specific security check by its ID.
+
+    IMPORTANT: This tool returns COMPLETE check details.
+    Use this after finding a specific check ID, you can get it via `prowler_hub_list_checks` or `prowler_hub_semantic_search_checks`.
+
+    Returns:
+        {
+          "id": "string",
+          "title": "string",
+          "description": "string",
+          "provider": "string",
+          "service": "string",
+          "severity": "low",
+          "risk": "string",
+          "reference": [
+            "string"
+          ],
+          "additional_urls": [
+            "string"
+          ],
+          "remediation": {
+            "cli": {
+              "description": "string"
+            },
+            "terraform": {
+              "description": "string"
+            },
+            "nativeiac": {
+              "description": "string"
+            },
+            "other": {
+              "description": "string"
+            },
+            "wui": {
+              "description": "string",
+              "reference": "string"
+            }
+          },
+          "services_required": [
+            "string"
+          ],
+          "notes": "string",
+          "compliances": [
+            {
+              "name": "string",
+              "id": "string"
+            }
+          ],
+          "categories": [
+            "string"
+          ],
+          "resource_type": "string",
+          "related_url": "string",
+          "fixer": bool
+        }
+
+    Useful Example Workflow:
+    1. Use `prowler_hub_list_checks` or `prowler_hub_search_checks` to find check IDs
+    2. Use this tool with the check 'id' to get complete information including remediation guidance
+    """
+    try:
+        response = prowler_hub_client.get(f"/check/{check_id}")
+        response.raise_for_status()
+        check = response.json()
+
+        if not check:
+            return {"error": f"Check '{check_id}' not found"}
+
+        # Build response with only non-empty fields to save tokens
+        result = {}
+
+        # Core fields
+        result["id"] = check["id"]
+        if check.get("title"):
+            result["title"] = check["title"]
+        if check.get("description"):
+            result["description"] = check["description"]
+        if check.get("provider"):
+            result["provider"] = check["provider"]
+        if check.get("service"):
+            result["service"] = check["service"]
+        if check.get("severity"):
+            result["severity"] = check["severity"]
+        if check.get("risk"):
+            result["risk"] = check["risk"]
+        if check.get("resource_type"):
+            result["resource_type"] = check["resource_type"]
+
+        # List fields
+        if check.get("reference"):
+            result["reference"] = check["reference"]
+        if check.get("additional_urls"):
+            result["additional_urls"] = check["additional_urls"]
+        if check.get("services_required"):
+            result["services_required"] = check["services_required"]
+        if check.get("categories"):
+            result["categories"] = check["categories"]
+        if check.get("compliances"):
+            result["compliances"] = check["compliances"]
+
+        # Other fields
+        if check.get("notes"):
+            result["notes"] = check["notes"]
+        if check.get("related_url"):
+            result["related_url"] = check["related_url"]
+        if check.get("fixer") is not None:
+            result["fixer"] = check["fixer"]
+
+        # Remediation - filter out empty nested values
+        remediation = check.get("remediation", {})
+        if remediation:
+            filtered_remediation = {}
+            for key, value in remediation.items():
+                if value and isinstance(value, dict):
+                    # Filter out empty values within nested dict
+                    filtered_value = {k: v for k, v in value.items() if v}
+                    if filtered_value:
+                        filtered_remediation[key] = filtered_value
+                elif value:
+                    filtered_remediation[key] = value
+            if filtered_remediation:
+                result["remediation"] = filtered_remediation
+
+        return result
+    except httpx.HTTPStatusError as e:
+        return {
+            "error": f"HTTP error {e.response.status_code}: {e.response.text}",
+        }
+    except Exception as e:
+        return {"error": str(e)}
+
 
 @hub_mcp_server.tool()
 async def get_check_code(
-    provider_id: str,
-    check_id: str,
-) -> dict[str, Any]:
-    """
-    Fetch the check implementation Python code from Prowler.
+    provider_id: str = Field(
+        description="Prowler Provider ID. Example: 'aws', 'azure', 'gcp', 'kubernetes'. Use `prowler_hub_list_providers` to get available provider IDs.",
+    ),
+    check_id: str = Field(
+        description="The check ID. Example: 's3_bucket_public_access'. Get IDs from `prowler_hub_list_checks` or `prowler_hub_search_checks`.",
+    ),
+) -> dict:
+    """Fetch the Python implementation code of a Prowler security check.
 
-    Args:
-        provider_id: Prowler provider ID (e.g., "aws", "azure").
-        check_id: Prowler check ID (e.g., "opensearch_service_domains_not_publicly_accessible").
+    The check code shows exactly how Prowler evaluates resources for security issues.
+    Use this to understand check logic, customize checks, or create new ones.
 
     Returns:
-        Dict with the code content as text.
+        {
+            "content": "Python source code of the check implementation"
+        }
     """
     if provider_id and check_id:
         url = github_check_path(provider_id, check_id, ".py")
@@ -251,18 +392,29 @@ async def get_check_code(
 
 @hub_mcp_server.tool()
 async def get_check_fixer(
-    provider_id: str,
-    check_id: str,
-) -> dict[str, Any]:
-    """
-    Fetch the check fixer Python code from Prowler, if it exists.
+    provider_id: str = Field(
+        description="Prowler Provider ID. Example: 'aws', 'azure', 'gcp', 'kubernetes'. Use `prowler_hub_list_providers` to get available provider IDs.",
+    ),
+    check_id: str = Field(
+        description="The check ID. Example: 's3_bucket_public_access'. Get IDs from `prowler_hub_list_checks` or `prowler_hub_search_checks`.",
+    ),
+) -> dict:
+    """Fetch the auto-remediation (fixer) code for a Prowler security check.
 
-    Args:
-        provider_id: Prowler provider ID (e.g., "aws", "azure").
-        check_id: Prowler check ID (e.g., "opensearch_service_domains_not_publicly_accessible").
+    IMPORTANT: Not all checks have fixers. A "fixer not found" response means the check
+    doesn't have auto-remediation code - this is normal for many checks.
+
+    Fixer code provides automated remediation that can fix security issues detected by checks.
+    Use this to understand how to programmatically remediate findings.
 
     Returns:
-        Dict with fixer content as text if present, existence flag.
+        {
+            "content": "Python source code of the auto-remediation implementation"
+        }
+        Or if no fixer exists:
+        {
+            "error": "Fixer not found for check {check_id}"
+        }
     """
     if provider_id and check_id:
         url = github_check_path(provider_id, check_id, "_fixer.py")
@@ -295,95 +447,66 @@ async def get_check_fixer(
         }
 
 
-@hub_mcp_server.tool()
-async def search_checks(term: str) -> dict[str, Any]:
-    """
-    Search the term across all text properties of check metadata.
-
-    Args:
-        term: Search term to find in check titles, descriptions, and other text fields
-
-    Returns:
-        List of checks matching the search term
-    """
-    try:
-        response = prowler_hub_client.get("/check/search", params={"term": term})
-        response.raise_for_status()
-        checks = response.json()
-
-        return {
-            "count": len(checks),
-            "checks": checks,
-        }
-    except httpx.HTTPStatusError as e:
-        return {
-            "error": f"HTTP error {e.response.status_code}: {e.response.text}",
-        }
-    except Exception as e:
-        return {"error": str(e)}
-
-
 # Compliance Framework Tools
 @hub_mcp_server.tool()
-async def get_compliance_frameworks(
-    provider: Optional[str] = None,
-    fields: Optional[
-        str
-    ] = "id,framework,provider,description,total_checks,total_requirements",
-) -> dict[str, Any]:
-    """
-    List and filter compliance frameworks. The list can be filtered by the parameters defined for the tool.
+async def list_compliances(
+    provider: list[str] = Field(
+        default=[],
+        description="Filter by cloud provider. Example: ['aws']. Use `prowler_hub_list_providers` to get available provider IDs.",
+    ),
+) -> dict:
+    """List compliance frameworks supported by Prowler.
 
-    Args:
-        provider: Filter by one Prowler provider ID. Example: "aws". Use the tool `list_providers` to get the available providers IDs.
-        fields: Specify which fields to return (id is always included). Example: "id,provider,description,version".
-                It is recommended to run with the default parameters because the full response is too large.
-                Available values are "id", "framework", "provider", "description", "total_checks", "total_requirements", "created_at", "updated_at".
-                The default parameters are "id,framework,provider,description,total_checks,total_requirements".
-                If null, all fields will be returned.
+    IMPORTANT: This tool returns LIGHTWEIGHT compliance data. Use this for fast browsing and filtering.
+    For complete details including requirements use `prowler_hub_get_compliance_details`.
+
+    Compliance frameworks define sets of security requirements that checks map to.
+    Use this to discover available frameworks for compliance reporting.
+
+    WARNING: An unfiltered request may return a large number of frameworks. Use the provider with not more than 3 different providers to make easier the response handling.
 
     Returns:
-        List of compliance frameworks. The structure is as follows:
         {
             "count": N,
-            "frameworks": {
-                "framework_id": {
-                    "id": "framework_id",
-                    "provider": "provider_id",
-                    "description": "framework_description",
-                    "version": "framework_version"
-                }
-            }
+            "compliances": [
+                {
+                    "id": "cis_4.0_aws",
+                    "name": "CIS Amazon Web Services Foundations Benchmark v4.0",
+                    "provider": "aws",
+                },
+                ...
+            ]
         }
+
+    Useful Example Workflow:
+    1. Use `prowler_hub_list_providers` to see available cloud providers
+    2. Use this tool to browse compliance frameworks
+    3. Use `prowler_hub_get_compliance_details` with the compliance 'id' to get complete information
     """
-    params = {}
+    # Lightweight fields for listing
+    lightweight_fields = "id,name,provider"
+
+    params: dict[str, str] = {"fields": lightweight_fields}
 
     if provider:
-        params["provider"] = provider
-    if fields:
-        params["fields"] = fields
+        params["provider"] = ",".join(provider)
 
     try:
         response = prowler_hub_client.get("/compliance", params=params)
         response.raise_for_status()
-        frameworks = response.json()
+        compliances = response.json()
 
-        frameworks_dict = {}
-        for framework in frameworks:
-            framework_data = {}
-            # Always include the id field as it's mandatory for the response structure
-            if "id" in framework:
-                framework_data["id"] = framework["id"]
+        # Return compliances as a lightweight list
+        compliances_list = []
+        for compliance in compliances:
+            compliance_data = {
+                "id": compliance["id"],
+                "name": compliance["name"],
+                "provider": compliance["provider"],
+            }
+            compliances_list.append(compliance_data)
 
-            # Include other requested fields
-            for field in fields.split(","):
-                if (
-                    field != "id" and field in framework
-                ):  # Skip id since it's already added
-                    framework_data[field] = framework[field]
-            frameworks_dict[framework["id"]] = framework_data
-
-        return {"count": len(frameworks), "frameworks": frameworks_dict}
+        return {"count": len(compliances), "compliances": compliances_list}
     except httpx.HTTPStatusError as e:
         return {
             "error": f"HTTP error {e.response.status_code}: {e.response.text}",
@@ -393,26 +516,48 @@ async def get_compliance_frameworks(
 
 
 @hub_mcp_server.tool()
-async def search_compliance_frameworks(term: str) -> dict[str, Any]:
-    """
-    Search compliance frameworks by term.
+async def semantic_search_compliances(
+    term: str = Field(
+        description="Search term. Examples: 'CIS', 'HIPAA', 'PCI', 'GDPR', 'SOC2', 'NIST'.",
+    ),
+) -> dict:
+    """Search for compliance frameworks using free-text search.
 
-    Args:
-        term: Search term to find in framework names and descriptions
+    IMPORTANT: This tool returns LIGHTWEIGHT compliance data. Use this for discovering frameworks by topic.
+    For complete details including requirements use `prowler_hub_get_compliance_details`.
+
+    Searches across framework names, descriptions, and metadata. Use this when you
+    want to find frameworks related to a specific regulation, standard, or topic.
 
     Returns:
-        List of compliance frameworks matching the search term
+        {
+            "count": N,
+            "compliances": [
+                {
+                    "id": "cis_4.0_aws",
+                    "name": "CIS Amazon Web Services Foundations Benchmark v4.0",
+                    "provider": "aws",
+                },
+                ...
+            ]
+        }
     """
     try:
         response = prowler_hub_client.get("/compliance/search", params={"term": term})
         response.raise_for_status()
-        frameworks = response.json()
+        compliances = response.json()
 
-        return {
-            "count": len(frameworks),
-            "search_term": term,
-            "frameworks": frameworks,
-        }
+        # Return compliances as a lightweight list
+        compliances_list = []
+        for compliance in compliances:
+            compliance_data = {
+                "id": compliance["id"],
+                "name": compliance["name"],
+                "provider": compliance["provider"],
+            }
+            compliances_list.append(compliance_data)
+
+        return {"count": len(compliances), "compliances": compliances_list}
     except httpx.HTTPStatusError as e:
         return {
             "error": f"HTTP error {e.response.status_code}: {e.response.text}",
@@ -421,22 +566,121 @@ async def search_compliance_frameworks(term: str) -> dict[str, Any]:
         return {"error": str(e)}
 
 
+@hub_mcp_server.tool()
+async def get_compliance_details(
+    compliance_id: str = Field(
+        description="The compliance framework ID to retrieve details for. Example: 'cis_4.0_aws'. Use `prowler_hub_list_compliances` or `prowler_hub_semantic_search_compliances` to find available compliance IDs.",
+    ),
+) -> dict:
+    """Retrieve comprehensive details about a specific compliance framework by its ID.
+
+    IMPORTANT: This tool returns COMPLETE compliance details.
+    Use this after finding a specific compliance via `prowler_hub_list_compliances` or `prowler_hub_semantic_search_compliances`.
+
+    Returns:
+        {
+            "id": "string",
+            "name": "string",
+            "framework": "string",
+            "provider": "string",
+            "version": "string",
+            "description": "string",
+            "total_checks": int,
+            "total_requirements": int,
+            "requirements": [
+                {
+                    "id": "string",
+                    "name": "string",
+                    "description": "string",
+                    "checks": ["check_id_1", "check_id_2"]
+                }
+            ]
+        }
+    """
+    try:
+        response = prowler_hub_client.get(f"/compliance/{compliance_id}")
+        response.raise_for_status()
+        compliance = response.json()
+
+        if not compliance:
+            return {"error": f"Compliance '{compliance_id}' not found"}
+
+        # Build response with only non-empty fields to save tokens
+        result = {}
+
+        # Core fields
+        result["id"] = compliance["id"]
+        if compliance.get("name"):
+            result["name"] = compliance["name"]
+        if compliance.get("framework"):
+            result["framework"] = compliance["framework"]
+        if compliance.get("provider"):
+            result["provider"] = compliance["provider"]
+        if compliance.get("version"):
+            result["version"] = compliance["version"]
+        if compliance.get("description"):
+            result["description"] = compliance["description"]
+
+        # Numeric fields
+        if compliance.get("total_checks"):
+            result["total_checks"] = compliance["total_checks"]
+        if compliance.get("total_requirements"):
+            result["total_requirements"] = compliance["total_requirements"]
+
+        # Requirements - filter out empty nested values
+        requirements = compliance.get("requirements", [])
+        if requirements:
+            filtered_requirements = []
+            for req in requirements:
+                filtered_req = {}
+                if req.get("id"):
+                    filtered_req["id"] = req["id"]
+                if req.get("name"):
+                    filtered_req["name"] = req["name"]
+                if req.get("description"):
+                    filtered_req["description"] = req["description"]
+                if req.get("checks"):
+                    filtered_req["checks"] = req["checks"]
+                if filtered_req:
+                    filtered_requirements.append(filtered_req)
+            if filtered_requirements:
+                result["requirements"] = filtered_requirements
+
+        return result
+    except httpx.HTTPStatusError as e:
+        if e.response.status_code == 404:
+            return {"error": f"Compliance '{compliance_id}' not found"}
+        return {
+            "error": f"HTTP error {e.response.status_code}: {e.response.text}",
+        }
+    except Exception as e:
+        return {"error": str(e)}
+
+
 # Provider Tools
 @hub_mcp_server.tool()
-async def list_providers() -> dict[str, Any]:
-    """
-    Get all available Prowler providers and their associated services.
+async def list_providers() -> dict:
+    """List all providers supported by Prowler.
+
+    This is a reference tool that shows available providers (aws, azure, gcp, kubernetes, etc.)
+    that can be scanned for finding security issues.
+
+    Use the provider IDs from this tool as filter values in other tools.
 
     Returns:
-        List of Prowler providers with their associated services. The structure is as follows:
         {
             "count": N,
-            "providers": {
-                "provider_id": {
-                    "name": "provider_name",
-                    "services": ["service_id_1", "service_id_2", "service_id_3", ...]
-                }
-            }
+            "providers": [
+                {
+                    "id": "aws",
+                    "name": "Amazon Web Services"
+                },
+                {
+                    "id": "azure",
+                    "name": "Microsoft Azure"
+                },
+                ...
+            ]
         }
     """
     try:
@@ -444,14 +688,16 @@ async def list_providers() -> dict[str, Any]:
         response.raise_for_status()
         providers = response.json()
 
-        providers_dict = {}
+        providers_list = []
         for provider in providers:
-            providers_dict[provider["id"]] = {
-                "name": provider.get("name", ""),
-                "services": provider.get("services", []),
-            }
+            providers_list.append(
+                {
+                    "id": provider["id"],
+                    "name": provider.get("name", ""),
+                }
+            )
 
-        return {"count": len(providers), "providers": providers_dict}
+        return {"count": len(providers), "providers": providers_list}
     except httpx.HTTPStatusError as e:
         return {
             "error": f"HTTP error {e.response.status_code}: {e.response.text}",
@@ -460,24 +706,42 @@ async def list_providers() -> dict[str, Any]:
         return {"error": str(e)}
 
 
-# Analytics Tools
 @hub_mcp_server.tool()
-async def get_artifacts_count() -> dict[str, Any]:
-    """
-    Get total count of security artifacts (checks + compliance frameworks).
+async def get_provider_services(
+    provider_id: str = Field(
+        description="The provider ID to get services for. Example: 'aws', 'azure', 'gcp', 'kubernetes'. Use `prowler_hub_list_providers` to get available provider IDs.",
+    ),
+) -> dict:
+    """Get the list of services IDs available for a specific cloud provider.
+
+    Services represent the different resources and capabilities that Prowler can scan
+    within a provider (e.g., s3, ec2, iam for AWS or keyvault, storage for Azure).
+
+    Use service IDs from this tool as filter values in other tools.
 
     Returns:
-        Total number of artifacts in the Prowler Hub.
+        {
+            "provider_id": "aws",
+            "provider_name": "Amazon Web Services",
+            "count": N,
+            "services": ["s3", "ec2", "iam", "rds", "lambda", ...]
+        }
     """
     try:
-        response = prowler_hub_client.get("/n_artifacts")
+        response = prowler_hub_client.get("/providers")
         response.raise_for_status()
-        data = response.json()
+        providers = response.json()
 
-        return {
-            "total_artifacts": data.get("n", 0),
-            "details": "Total count includes both security checks and compliance frameworks",
-        }
+        for provider in providers:
+            if provider["id"] == provider_id:
+                return {
+                    "provider_id": provider["id"],
+                    "provider_name": provider.get("name", ""),
+                    "count": len(provider.get("services", [])),
+                    "services": provider.get("services", []),
+                }
+
+        return {"error": f"Provider '{provider_id}' not found"}
     except httpx.HTTPStatusError as e:
         return {
             "error": f"HTTP error {e.response.status_code}: {e.response.text}",

mcp_server/pyproject.toml

@@ -11,7 +11,7 @@ description = "MCP server for Prowler ecosystem"
 name = "prowler-mcp"
 readme = "README.md"
 requires-python = ">=3.12"
-version = "0.1.0"
+version = "0.3.0"
 
 [project.scripts]
 generate-prowler-app-mcp-server = "prowler_mcp_server.prowler_app.utils.server_generator:generate_server_file"

mcp_server/uv.lock

@@ -603,7 +603,7 @@ wheels = [
 
 [[package]]
 name = "prowler-mcp"
-version = "0.1.0"
+version = "0.3.0"
 source = { editable = "." }
 dependencies = [
     { name = "fastmcp" },

prowler/CHANGELOG.md

@@ -2,10 +2,51 @@
 
 All notable changes to the **Prowler SDK** are documented in this file.
 
+## [5.17.0] (Prowler UNRELEASED)
+
+### Added
+- Add Prowler ThreatScore for the Alibaba Cloud provider [(#9511)](https://github.com/prowler-cloud/prowler/pull/9511)
+
+### Changed
+- Update AWS Step Functions service metadata to new format [(#9432)](https://github.com/prowler-cloud/prowler/pull/9432)
+- Update AWS Route 53 service metadata to new format [(#9406)](https://github.com/prowler-cloud/prowler/pull/9406)
+- Update AWS SQS service metadata to new format [(#9429)](https://github.com/prowler-cloud/prowler/pull/9429)
+
+---
+
+## [5.16.0] (Prowler v5.16.0)
+
+### Added
+
+- `privilege-escalation` and `ec2-imdsv1` categories for AWS checks [(#9537)](https://github.com/prowler-cloud/prowler/pull/9537)
+- Supported IaC formats and scanner documentation for the IaC provider [(#9553)](https://github.com/prowler-cloud/prowler/pull/9553)
+
+### Changed
+
+- Update AWS Glue service metadata to new format [(#9258)](https://github.com/prowler-cloud/prowler/pull/9258)
+- Update AWS Kafka service metadata to new format [(#9261)](https://github.com/prowler-cloud/prowler/pull/9261)
+- Update AWS KMS service metadata to new format [(#9263)](https://github.com/prowler-cloud/prowler/pull/9263)
+- Update AWS MemoryDB service metadata to new format [(#9266)](https://github.com/prowler-cloud/prowler/pull/9266)
+- Update AWS Inspector v2 service metadata to new format [(#9260)](https://github.com/prowler-cloud/prowler/pull/9260)
+- Update AWS Service Catalog service metadata to new format [(#9410)](https://github.com/prowler-cloud/prowler/pull/9410)
+- Update AWS SNS service metadata to new format [(#9428)](https://github.com/prowler-cloud/prowler/pull/9428)
+- Update AWS Trusted Advisor service metadata to new format [(#9435)](https://github.com/prowler-cloud/prowler/pull/9435)
+- Update AWS WAF service metadata to new format [(#9480)](https://github.com/prowler-cloud/prowler/pull/9480)
+- Update AWS WAF v2 service metadata to new format [(#9481)](https://github.com/prowler-cloud/prowler/pull/9481)
+
+### Fixed
+- Fix typo `trustboundaries` category to `trust-boundaries` [(#9536)](https://github.com/prowler-cloud/prowler/pull/9536)
+- Fix incorrect `bedrock-agent` regional availability, now using official AWS docs instead of copying from `bedrock`
+- Store MongoDB Atlas provider regions as lowercase [(#9554)](https://github.com/prowler-cloud/prowler/pull/9554)
+- Store GCP Cloud Storage bucket regions as lowercase [(#9567)](https://github.com/prowler-cloud/prowler/pull/9567)
+
+---
+
 ## [5.15.1] (Prowler v5.15.1)
 
 ### Fixed
 - Fix false negative in AWS `apigateway_restapi_logging_enabled` check by refining stage logging evaluation to ensure logging level is not set to "OFF" [(#9304)](https://github.com/prowler-cloud/prowler/pull/9304)
+
 ---
 
 ## [5.15.0] (Prowler v5.15.0)

prowler/__main__.py

@@ -83,6 +83,9 @@ from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_azure import (
     AzureMitreAttack,
 )
 from prowler.lib.outputs.compliance.mitre_attack.mitre_attack_gcp import GCPMitreAttack
+from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_alibaba import (
+    ProwlerThreatScoreAlibaba,
+)
 from prowler.lib.outputs.compliance.prowler_threatscore.prowler_threatscore_aws import (
     ProwlerThreatScoreAWS,
 )
@@ -1039,6 +1042,18 @@ def prowler():
                 )
                 generated_outputs["compliance"].append(cis)
                 cis.batch_write_data_to_file()
+            elif compliance_name == "prowler_threatscore_alibabacloud":
+                filename = (
+                    f"{output_options.output_directory}/compliance/"
+                    f"{output_options.output_filename}_{compliance_name}.csv"
+                )
+                prowler_threatscore = ProwlerThreatScoreAlibaba(
+                    findings=finding_outputs,
+                    compliance=bulk_compliance_frameworks[compliance_name],
+                    file_path=filename,
+                )
+                generated_outputs["compliance"].append(prowler_threatscore)
+                prowler_threatscore.batch_write_data_to_file()
             else:
                 filename = (
                     f"{output_options.output_directory}/compliance/"

prowler/config/config.py

@@ -38,7 +38,7 @@ class _MutableTimestamp:
 
 timestamp = _MutableTimestamp(datetime.today())
 timestamp_utc = _MutableTimestamp(datetime.now(timezone.utc))
-prowler_version = "5.15.1"
+prowler_version = "5.16.1"
 html_logo_url = "https://github.com/prowler-cloud/prowler/"
 square_logo_img = "https://raw.githubusercontent.com/prowler-cloud/prowler/dc7d2d5aeb92fdf12e8604f42ef6472cd3e8e889/docs/img/prowler-logo-black.png"
 aws_logo = "https://user-images.githubusercontent.com/38561120/235953920-3e3fba08-0795-41dc-b480-9bea57db9f2e.png"

prowler/lib/outputs/compliance/prowler_threatscore/models.py

@@ -146,3 +146,29 @@ class ProwlerThreatScoreKubernetesModel(BaseModel):
     Muted: bool
     Framework: str
     Name: str
+
+
+class ProwlerThreatScoreAlibabaModel(BaseModel):
+    """
+    ProwlerThreatScoreAlibabaModel generates a finding's output in Alibaba Cloud Prowler ThreatScore Compliance format.
+    """
+
+    Provider: str
+    Description: str
+    AccountId: str
+    Region: str
+    AssessmentDate: str
+    Requirements_Id: str
+    Requirements_Description: str
+    Requirements_Attributes_Title: str
+    Requirements_Attributes_Section: str
+    Requirements_Attributes_SubSection: Optional[str] = None
+    Requirements_Attributes_AttributeDescription: str
+    Requirements_Attributes_AdditionalInformation: str
+    Requirements_Attributes_LevelOfRisk: int
+    Requirements_Attributes_Weight: int
+    Status: str
+    StatusExtended: str
+    ResourceId: str
+    ResourceName: str
+    CheckId: str

prowler/lib/outputs/compliance/prowler_threatscore/prowler_threatscore_alibaba.py

@@ -0,0 +1,98 @@
+from prowler.config.config import timestamp
+from prowler.lib.check.compliance_models import Compliance
+from prowler.lib.outputs.compliance.compliance_output import ComplianceOutput
+from prowler.lib.outputs.compliance.prowler_threatscore.models import (
+    ProwlerThreatScoreAlibabaModel,
+)
+from prowler.lib.outputs.finding import Finding
+
+
+class ProwlerThreatScoreAlibaba(ComplianceOutput):
+    """
+    This class represents the Alibaba Cloud Prowler ThreatScore compliance output.
+
+    Attributes:
+        - _data (list): A list to store transformed data from findings.
+        - _file_descriptor (TextIOWrapper): A file descriptor to write data to a file.
+
+    Methods:
+        - transform: Transforms findings into Alibaba Cloud Prowler ThreatScore compliance format.
+    """
+
+    def transform(
+        self,
+        findings: list[Finding],
+        compliance: Compliance,
+        compliance_name: str,
+    ) -> None:
+        """
+        Transforms a list of findings into Alibaba Cloud Prowler ThreatScore compliance format.
+
+        Parameters:
+            - findings (list): A list of findings.
+            - compliance (Compliance): A compliance model.
+            - compliance_name (str): The name of the compliance model.
+
+        Returns:
+            - None
+        """
+        for finding in findings:
+            # Get the compliance requirements for the finding
+            finding_requirements = finding.compliance.get(compliance_name, [])
+            for requirement in compliance.Requirements:
+                if requirement.Id in finding_requirements:
+                    for attribute in requirement.Attributes:
+                        compliance_row = ProwlerThreatScoreAlibabaModel(
+                            Provider=finding.provider,
+                            Description=compliance.Description,
+                            AccountId=finding.account_uid,
+                            Region=finding.region,
+                            AssessmentDate=str(timestamp),
+                            Requirements_Id=requirement.Id,
+                            Requirements_Description=requirement.Description,
+                            Requirements_Attributes_Title=attribute.Title,
+                            Requirements_Attributes_Section=attribute.Section,
+                            Requirements_Attributes_SubSection=attribute.SubSection,
+                            Requirements_Attributes_AttributeDescription=attribute.AttributeDescription,
+                            Requirements_Attributes_AdditionalInformation=attribute.AdditionalInformation,
+                            Requirements_Attributes_LevelOfRisk=attribute.LevelOfRisk,
+                            Requirements_Attributes_Weight=attribute.Weight,
+                            Status=finding.status,
+                            StatusExtended=finding.status_extended,
+                            ResourceId=finding.resource_uid,
+                            ResourceName=finding.resource_name,
+                            CheckId=finding.check_id,
+                            Muted=finding.muted,
+                            Framework=compliance.Framework,
+                            Name=compliance.Name,
+                        )
+                        self._data.append(compliance_row)
+        # Add manual requirements to the compliance output
+        for requirement in compliance.Requirements:
+            if not requirement.Checks:
+                for attribute in requirement.Attributes:
+                    compliance_row = ProwlerThreatScoreAlibabaModel(
+                        Provider=compliance.Provider.lower(),
+                        Description=compliance.Description,
+                        AccountId="",
+                        Region="",
+                        AssessmentDate=str(timestamp),
+                        Requirements_Id=requirement.Id,
+                        Requirements_Description=requirement.Description,
+                        Requirements_Attributes_Title=attribute.Title,
+                        Requirements_Attributes_Section=attribute.Section,
+                        Requirements_Attributes_SubSection=attribute.SubSection,
+                        Requirements_Attributes_AttributeDescription=attribute.AttributeDescription,
+                        Requirements_Attributes_AdditionalInformation=attribute.AdditionalInformation,
+                        Requirements_Attributes_LevelOfRisk=attribute.LevelOfRisk,
+                        Requirements_Attributes_Weight=attribute.Weight,
+                        Status="MANUAL",
+                        StatusExtended="Manual check",
+                        ResourceId="manual_check",
+                        ResourceName="Manual check",
+                        CheckId="manual",
+                        Muted=False,
+                        Framework=compliance.Framework,
+                        Name=compliance.Name,
+                    )
+                    self._data.append(compliance_row)

prowler/providers/aws/aws_regions_by_service.json

@@ -1426,42 +1426,23 @@
     "bedrock-agent": {
       "regions": {
         "aws": [
-          "af-south-1",
-          "ap-east-2",
           "ap-northeast-1",
           "ap-northeast-2",
-          "ap-northeast-3",
           "ap-south-1",
-          "ap-south-2",
           "ap-southeast-1",
           "ap-southeast-2",
-          "ap-southeast-3",
-          "ap-southeast-4",
-          "ap-southeast-5",
-          "ap-southeast-7",
           "ca-central-1",
-          "ca-west-1",
           "eu-central-1",
           "eu-central-2",
-          "eu-north-1",
-          "eu-south-1",
-          "eu-south-2",
           "eu-west-1",
           "eu-west-2",
           "eu-west-3",
-          "il-central-1",
-          "me-central-1",
-          "me-south-1",
-          "mx-central-1",
           "sa-east-1",
           "us-east-1",
-          "us-east-2",
-          "us-west-1",
           "us-west-2"
         ],
         "aws-cn": [],
         "aws-us-gov": [
-          "us-gov-east-1",
           "us-gov-west-1"
         ]
       }
@@ -12583,4 +12564,4 @@
       }
     }
   }
-}
+}

prowler/providers/aws/services/bedrock/bedrock_api_key_no_administrative_privileges/bedrock_api_key_no_administrative_privileges.metadata.json

@@ -28,7 +28,7 @@
   },
   "Categories": [
     "gen-ai",
-    "trustboundaries"
+    "trust-boundaries"
   ],
   "DependsOn": [],
   "RelatedTo": [],

prowler/providers/aws/services/bedrock/bedrock_api_key_no_long_term_credentials/bedrock_api_key_no_long_term_credentials.metadata.json

@@ -28,7 +28,7 @@
   },
   "Categories": [
     "gen-ai",
-    "trustboundaries"
+    "trust-boundaries"
   ],
   "DependsOn": [],
   "RelatedTo": [],

prowler/providers/aws/services/ec2/ec2_instance_account_imdsv2_enabled/ec2_instance_account_imdsv2_enabled.metadata.json

@@ -26,7 +26,8 @@
     }
   },
   "Categories": [
-    "internet-exposed"
+    "internet-exposed",
+    "ec2-imdsv1"
   ],
   "DependsOn": [],
   "RelatedTo": [],

prowler/providers/aws/services/ec2/ec2_instance_imdsv2_enabled/ec2_instance_imdsv2_enabled.metadata.json

@@ -25,7 +25,9 @@
       "Url": "https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/configuring-instance-metadata-service.html#configuring-instance-metadata-options"
     }
   },
-  "Categories": [],
+  "Categories": [
+    "ec2-imdsv1"
+  ],
   "DependsOn": [],
   "RelatedTo": [],
   "Notes": ""

prowler/providers/aws/services/ec2/ec2_instance_uses_single_eni/ec2_instance_uses_single_eni.metadata.json

@@ -26,7 +26,7 @@
     }
   },
   "Categories": [
-    "trustboundaries"
+    "trust-boundaries"
   ],
   "DependsOn": [],
   "RelatedTo": [],

prowler/providers/aws/services/glue/glue_data_catalogs_connection_passwords_encryption_enabled/glue_data_catalogs_connection_passwords_encryption_enabled.metadata.json

@@ -1,28 +1,34 @@
 {
   "Provider": "aws",
   "CheckID": "glue_data_catalogs_connection_passwords_encryption_enabled",
-  "CheckTitle": "Check if Glue data catalog settings have encrypt connection password enabled.",
+  "CheckTitle": "Glue data catalog connection password is encrypted with a KMS key",
   "CheckType": [
+    "Software and Configuration Checks/AWS Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
     "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
-  "Severity": "medium",
+  "ResourceIdTemplate": "",
+  "Severity": "high",
   "ResourceType": "Other",
-  "Description": "Check if Glue data catalog settings have encrypt connection password enabled.",
-  "Risk": "If not enabled sensitive information at rest is not protected.",
+  "Description": "**AWS Glue Data Catalog** settings for **connection password encryption** are evaluated to confirm an AWS KMS key is configured to encrypt passwords stored in connection properties.",
+  "Risk": "Unencrypted connection passwords can be read from the catalog or responses, letting attackers or over-privileged users obtain database credentials. This jeopardizes confidentiality of linked data stores, enables unauthorized modifications, and can facilitate lateral movement across environments.",
   "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/aws-glue-api-jobs-security.html",
+    "https://docs.aws.amazon.com/glue/latest/dg/encrypt-connection-passwords.html"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue put-data-catalog-encryption-settings --data-catalog-encryption-settings ConnectionPasswordEncryption={ReturnConnectionPasswordEncrypted=True,AwsKmsKeyId=<ksm_key_arn>",
-      "NativeIaC": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_37#cloudformation",
-      "Other": "",
-      "Terraform": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_37#terraform"
+      "CLI": "aws glue put-data-catalog-encryption-settings --data-catalog-encryption-settings '{\"ConnectionPasswordEncryption\":{\"ReturnConnectionPasswordEncrypted\":true,\"AwsKmsKeyId\":\"<kms_key_arn>\"}}'",
+      "NativeIaC": "```yaml\n# CloudFormation: enable Glue Data Catalog connection password encryption\nResources:\n  <example_resource_name>:\n    Type: AWS::Glue::DataCatalogEncryptionSettings\n    Properties:\n      DataCatalogEncryptionSettings:\n        ConnectionPasswordEncryption:\n          ReturnConnectionPasswordEncrypted: true  # Critical: encrypts connection passwords\n          KmsKeyId: <kms_key_arn>  # Critical: KMS key used for encryption\n```",
+      "Other": "1. In the AWS Console, go to AWS Glue\n2. Click Settings (left menu)\n3. Under Data catalog settings, check Encrypt connection passwords\n4. Select your KMS key (symmetric CMK)\n5. Click Save",
+      "Terraform": "```hcl\n# Enable Glue Data Catalog connection password encryption\nresource \"aws_glue_data_catalog_encryption_settings\" \"<example_resource_name>\" {\n  data_catalog_encryption_settings {\n    # Critical: enables password encryption with a KMS key\n    connection_password_encryption {\n      return_connection_password_encrypted = true\n      aws_kms_key_id                       = \"<kms_key_arn>\"\n    }\n\n    # Required block for this resource; keep minimal\n    encryption_at_rest {\n      catalog_encryption_mode = \"DISABLED\"\n    }\n  }\n}\n```"
     },
     "Recommendation": {
-      "Text": "On the AWS Glue console, you can enable this option on the Data catalog settings page.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/encrypt-connection-passwords.html"
+      "Text": "Enable **connection password encryption** in the Data Catalog with a customer-managed KMS key.\n- Apply **least privilege** to the KMS key and Glue roles\n- Prefer keeping responses encrypted (`ReturnConnectionPasswordEncrypted`)\n- Rotate keys and monitor access for **defense in depth**",
+      "Url": "https://hub.prowler.com/check/glue_data_catalogs_connection_passwords_encryption_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_data_catalogs_metadata_encryption_enabled/glue_data_catalogs_metadata_encryption_enabled.metadata.json

@@ -1,28 +1,35 @@
 {
   "Provider": "aws",
   "CheckID": "glue_data_catalogs_metadata_encryption_enabled",
-  "CheckTitle": "Check if Glue data catalog settings have metadata encryption enabled.",
+  "CheckTitle": "Glue Data Catalog metadata is encrypted with KMS",
   "CheckType": [
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
     "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
+  "ResourceIdTemplate": "",
   "Severity": "medium",
   "ResourceType": "Other",
-  "Description": "Check if Glue data catalog settings have metadata encryption enabled.",
-  "Risk": "If not enabled sensitive information at rest is not protected.",
+  "Description": "**AWS Glue Data Catalog** metadata is encrypted at rest when catalog settings use **SSE-KMS** with a KMS key.\n\nCatalogs that do not configure `SSE-KMS` for metadata are considered unencrypted.",
+  "Risk": "Unencrypted catalog metadata exposes schemas, partitions, and data locations, reducing **confidentiality**.\n\nAdversaries or over-privileged users can conduct **reconnaissance** and plan lateral movement; tampering with definitions can corrupt queries and results, impacting **integrity**.",
   "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/encrypt-glue-data-catalog.html",
+    "https://docs.amazonaws.cn/en_us/athena/latest/ug/encryption.html",
+    "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/data-catalog-encryption-at-rest-with-cmk.html",
+    "https://support.icompaas.com/support/solutions/articles/62000233381-ensure-glue-data-catalogs-are-not-publicly-accessible-"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue put-data-catalog-encryption-settings --data-catalog-encryption-settings EncryptionAtRest={CatalogEncryptionMode=SSE-KMS,SseAwsKmsKeyId=<ksm_key_arn>",
-      "NativeIaC": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_37#cloudformation",
-      "Other": "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/data-catalog-encryption-at-rest.html",
-      "Terraform": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_37#terraform"
+      "CLI": "aws glue put-data-catalog-encryption-settings --data-catalog-encryption-settings '{\"EncryptionAtRest\":{\"CatalogEncryptionMode\":\"SSE-KMS\"}}'",
+      "NativeIaC": "```yaml\n# Enable Glue Data Catalog metadata encryption with KMS\nResources:\n  <example_resource_name>:\n    Type: AWS::Glue::DataCatalogEncryptionSettings\n    Properties:\n      DataCatalogEncryptionSettings:\n        EncryptionAtRest:\n          CatalogEncryptionMode: SSE-KMS  # Critical: enables KMS encryption for catalog metadata\n```",
+      "Other": "1. In the AWS Console, go to AWS Glue\n2. Open Data Catalog > Settings\n3. Under Security configuration and encryption, check Metadata encryption\n4. Leave the default AWS managed key selected (or choose a KMS key)\n5. Click Save",
+      "Terraform": "```hcl\n# Enable Glue Data Catalog metadata encryption with KMS\nresource \"aws_glue_data_catalog_encryption_settings\" \"<example_resource_name>\" {\n  data_catalog_encryption_settings {\n    encryption_at_rest {\n      catalog_encryption_mode = \"SSE-KMS\" # Critical: turns on KMS encryption for catalog metadata\n    }\n  }\n}\n```"
     },
     "Recommendation": {
-      "Text": "Enable Encryption. Use a CMK where possible. It will provide additional management and privacy benefits.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/encrypt-glue-data-catalog.html"
+      "Text": "Enable metadata encryption with **`SSE-KMS`**, preferably using a **customer-managed KMS key** for control and rotation.\n\nApply **least privilege** to KMS and catalog access, restrict who can change settings, and monitor key usage. Use **defense in depth** by encrypting related analytics assets consistently.",
+      "Url": "https://hub.prowler.com/check/glue_data_catalogs_metadata_encryption_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_data_catalogs_not_publicly_accessible/glue_data_catalogs_not_publicly_accessible.metadata.json

@@ -1,28 +1,35 @@
 {
   "Provider": "aws",
   "CheckID": "glue_data_catalogs_not_publicly_accessible",
-  "CheckTitle": "Ensure Glue Data Catalogs are not publicly accessible.",
+  "CheckTitle": "Glue Data Catalog is not publicly accessible via its resource policy",
   "CheckType": [
-    "Software and Configuration Checks/AWS Security Best Practices"
+    "Software and Configuration Checks/AWS Security Best Practices/Network Reachability",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
+    "TTPs/Initial Access",
+    "Effects/Data Exposure"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:aws:glue:region:account-id:catalog",
+  "ResourceIdTemplate": "",
   "Severity": "high",
-  "ResourceType": "AwsGlueDataCatalog",
-  "Description": "This control checks whether Glue Data Catalogs are not publicly accessible via resource policies.",
-  "Risk": "Publicly accessible Glue Data Catalogs can expose sensitive data schema and metadata, leading to potential security risks.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/security_iam_service-with-iam.html?icmpid=docs_console_unmapped#security_iam_service-with-iam-resource-based-policies",
+  "ResourceType": "Other",
+  "Description": "**AWS Glue Data Catalog** resource policies are assessed for configurations that expose the catalog to anyone, such as `Principal: *`, broad resource scopes, or permissive conditions.\n\nThe finding highlights catalogs made public through overly permissive resource-based access.",
+  "Risk": "Public catalog access lets unauthorized actors enumerate schemas, S3 locations, and connection metadata, weakening **confidentiality**. If writes are exposed, attackers can alter databases/tables, corrupt lineage, and disrupt jobs and queries, harming **integrity** and **availability**, and enabling lateral movement to data stores.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/security_iam_service-with-iam.html?icmpid=docs_console_unmapped#security_iam_service-with-iam-resource-based-policies",
+    "https://docs.aws.amazon.com/glue/latest/dg/cross-account-access.html"
+  ],
   "Remediation": {
     "Code": {
       "CLI": "aws glue delete-resource-policy",
       "NativeIaC": "",
-      "Other": "",
-      "Terraform": ""
+      "Other": "1. Sign in to the AWS Console and open the Glue service\n2. In the left menu, click Settings\n3. Under Data catalog settings > Permissions, click Edit resource policy\n4. Remove any statement that has Principal set to * (public) or AWS: \"*\"; or delete the entire policy\n5. Click Save",
+      "Terraform": "```hcl\nresource \"aws_glue_resource_policy\" \"<example_resource_name>\" {\n  policy = jsonencode({\n    Version   = \"2012-10-17\",\n    Statement = [\n      {\n        Effect    = \"Allow\",\n        Principal = { AWS = \"arn:aws:iam::<ACCOUNT_ID>:root\" } # Critical: restricts to your account, removing any public (*) access\n        Action    = \"glue:*\",\n        Resource  = \"arn:aws:glue:<REGION>:<ACCOUNT_ID>:catalog\"\n      }\n    ]\n  })\n}\n```"
     },
     "Recommendation": {
-      "Text": "Review Glue Data Catalog policies and ensure they are not publicly accessible. Implement the Principle of Least Privilege.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/security_iam_service-with-iam.html?icmpid=docs_console_unmapped#security_iam_service-with-iam-resource-based-policies"
+      "Text": "Enforce **least privilege** on catalog resource policies:\n- Avoid `Principal: *` and wildcards\n- Grant only required actions to explicit principals\n- Prefer identity-based access or Lake Formation for sharing\n- Limit scope with precise ARNs/conditions and monitor changes for **defense in depth**",
+      "Url": "https://hub.prowler.com/check/glue_data_catalogs_not_publicly_accessible"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_database_connections_ssl_enabled/glue_database_connections_ssl_enabled.metadata.json

@@ -1,28 +1,34 @@
 {
   "Provider": "aws",
   "CheckID": "glue_database_connections_ssl_enabled",
-  "CheckTitle": "Check if Glue database connection has SSL connection enabled.",
+  "CheckTitle": "Glue connection has SSL enabled",
   "CheckType": [
+    "Software and Configuration Checks/AWS Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
     "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
-  "Severity": "medium",
+  "ResourceIdTemplate": "",
+  "Severity": "high",
   "ResourceType": "Other",
-  "Description": "Check if Glue database connection has SSL connection enabled.",
-  "Risk": "Data exfiltration could happen if information is not protected in transit.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/encryption-in-transit.html",
+  "Description": "**AWS Glue connections** require **TLS/SSL** for JDBC when the `JDBC_ENFORCE_SSL` property is set to `true`.\n\nThis evaluates connection definitions to confirm SSL is enforced for traffic to external data stores.",
+  "Risk": "Absent TLS enforcement, JDBC traffic-including credentials, queries, and results-can be **intercepted or modified** in transit.\n\nThis enables:\n- Confidentiality loss via sniffing/MITM\n- Integrity tampering of queries/results\n- Credential theft leading to broader database access",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/encryption-in-transit.html",
+    "https://support.icompaas.com/support/solutions/articles/62000233690-ensure-glue-connections-have-ssl-enabled"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "",
-      "NativeIaC": "",
-      "Other": "",
-      "Terraform": ""
+      "CLI": "aws glue update-connection --name <example_resource_name> --connection-input '{\"Name\":\"<example_resource_name>\",\"ConnectionType\":\"JDBC\",\"ConnectionProperties\":{\"JDBC_CONNECTION_URL\":\"<example_jdbc_url>\",\"JDBC_ENFORCE_SSL\":\"true\"}}'",
+      "NativeIaC": "```yaml\n# CloudFormation: Enable SSL on a Glue JDBC connection\nResources:\n  <example_resource_name>:\n    Type: AWS::Glue::Connection\n    Properties:\n      ConnectionInput:\n        ConnectionType: JDBC\n        ConnectionProperties:\n          JDBC_CONNECTION_URL: \"<example_jdbc_url>\"\n          JDBC_ENFORCE_SSL: \"true\"  # Critical: forces SSL for the JDBC connection\n```",
+      "Other": "1. Open the AWS Console and go to AWS Glue > Data Catalog > Connections\n2. Select the connection and click Edit\n3. In Connection properties (Advanced properties), add key JDBC_ENFORCE_SSL with value true (or check Require SSL)\n4. Click Save",
+      "Terraform": "```hcl\n# Terraform: Enable SSL on a Glue JDBC connection\nresource \"aws_glue_connection\" \"<example_resource_name>\" {\n  name            = \"<example_resource_name>\"\n  connection_type = \"JDBC\"\n\n  connection_properties = {\n    JDBC_CONNECTION_URL = \"<example_jdbc_url>\"\n    JDBC_ENFORCE_SSL    = \"true\"  # Critical: forces SSL for the JDBC connection\n  }\n}\n```"
     },
     "Recommendation": {
-      "Text": "Configure encryption settings for crawlers, ETL jobs and development endpoints using security configurations in AWS Glue.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/encryption-in-transit.html"
+      "Text": "Enforce **TLS** on all Glue connections (set `JDBC_ENFORCE_SSL=true`) and require encryption on target databases.\n\nApply **defense in depth**: validate certificates, restrict network exposure, prefer private connectivity, and use **least-privilege** credentials with rotation.",
+      "Url": "https://hub.prowler.com/check/glue_database_connections_ssl_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_development_endpoints_cloudwatch_logs_encryption_enabled/glue_development_endpoints_cloudwatch_logs_encryption_enabled.metadata.json

@@ -1,28 +1,34 @@
 {
   "Provider": "aws",
   "CheckID": "glue_development_endpoints_cloudwatch_logs_encryption_enabled",
-  "CheckTitle": "Check if Glue development endpoints have CloudWatch logs encryption enabled.",
+  "CheckTitle": "Glue development endpoint has CloudWatch Logs encryption enabled",
   "CheckType": [
+    "Software and Configuration Checks/AWS Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
     "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
+  "ResourceIdTemplate": "",
   "Severity": "medium",
   "ResourceType": "Other",
-  "Description": "Check if Glue development endpoints have CloudWatch logs encryption enabled.",
-  "Risk": "If not enabled sensitive information at rest is not protected.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+  "Description": "**AWS Glue development endpoints** are assessed for an associated **security configuration** that enables **CloudWatch Logs encryption**. It confirms the endpoint references a configuration and that log encryption is not `DISABLED`.",
+  "Risk": "Unencrypted Glue logs erode **confidentiality**: credentials, connection strings, and data samples may be readable to unintended principals, enabling **lateral movement**.\nLack of KMS-backed encryption weakens **auditability** and **separation of duties**.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+    "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/cloud-watch-logs-encryption-enabled.html"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue create-security-configuration --name cw-encrypted-sec-config --encryption-configuration {'CloudWatchEncryption': [{'CloudWatchEncryptionMode': 'SSE-KMS','KmsKeyArn': <kms_arn>}]}",
-      "NativeIaC": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#cloudformation",
-      "Other": "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/cloud-watch-logs-encryption-enabled.html",
-      "Terraform": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#terraform"
+      "CLI": "",
+      "NativeIaC": "```yaml\n# CloudFormation: Glue Security Configuration with CloudWatch Logs encryption enabled\nResources:\n  <example_resource_name>:\n    Type: AWS::Glue::SecurityConfiguration\n    Properties:\n      Name: <example_resource_name>\n      EncryptionConfiguration:\n        CloudWatchEncryption:\n          CloudWatchEncryptionMode: SSE-KMS  # Critical: enables CloudWatch Logs encryption\n          KmsKeyArn: <kms_key_arn>           # Critical: KMS key used for encrypting Glue logs\n```",
+      "Other": "1. In the AWS Console, go to Glue > Security configurations > Add security configuration\n2. Enter a name and enable CloudWatch Logs encryption\n3. Select a KMS key (or enter its ARN) and click Create\n4. Go to Glue > Dev endpoints\n5. Create a new Dev endpoint (or delete and recreate the existing one) and select the new Security configuration\n6. Create the endpoint to apply the encryption",
+      "Terraform": "```hcl\n# Glue Security Configuration with CloudWatch Logs encryption enabled\nresource \"aws_glue_security_configuration\" \"<example_resource_name>\" {\n  name = \"<example_resource_name>\"\n\n  encryption_configuration {\n    cloudwatch_encryption {\n      cloudwatch_encryption_mode = \"SSE-KMS\"  # Critical: enables CloudWatch Logs encryption\n      kms_key_arn                = \"<kms_key_arn>\"  # Critical: KMS key used for encrypting Glue logs\n    }\n\n    # Required blocks for valid config (kept minimal)\n    job_bookmarks_encryption { job_bookmarks_encryption_mode = \"DISABLED\" }\n    s3_encryption             { s3_encryption_mode             = \"DISABLED\" }\n  }\n}\n```"
     },
     "Recommendation": {
-      "Text": "Enable Encryption in the Security configurations.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html"
+      "Text": "Attach a **security configuration** to all development endpoints with **CloudWatch Logs encryption** enabled using a tightly scoped **KMS key**.\nApply **least privilege** to key and log access, rotate keys, and standardize configs via IaC to enforce **defense in depth**.",
+      "Url": "https://hub.prowler.com/check/glue_development_endpoints_cloudwatch_logs_encryption_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_development_endpoints_job_bookmark_encryption_enabled/glue_development_endpoints_job_bookmark_encryption_enabled.metadata.json

@@ -1,28 +1,33 @@
 {
   "Provider": "aws",
   "CheckID": "glue_development_endpoints_job_bookmark_encryption_enabled",
-  "CheckTitle": "Check if Glue development endpoints have Job bookmark encryption enabled.",
+  "CheckTitle": "Glue development endpoint has Job Bookmark encryption enabled",
   "CheckType": [
-    "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
+    "Software and Configuration Checks/AWS Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
+  "ResourceIdTemplate": "",
   "Severity": "medium",
   "ResourceType": "Other",
-  "Description": "Check if Glue development endpoints have Job bookmark encryption enabled.",
-  "Risk": "If not enabled sensitive information at rest is not protected.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+  "Description": "**AWS Glue development endpoints** are assessed for an attached **security configuration** where **job bookmark encryption** is enabled. Endpoints lacking a security configuration are also identified.",
+  "Risk": "Unencrypted job bookmarks stored in S3 can be read or altered, exposing dataset paths, partitions, and processing state. This enables data discovery, state tampering, and replay/skip of workloads, impacting **confidentiality**, **integrity**, and **availability** of ETL pipelines.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+    "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/job-bookmark-encryption-enabled.html"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue create-security-configuration --name jb-encrypted-sec-config --encryption-configuration {'JobBookmarksEncryption': [{'JobBookmarksEncryptionMode': 'SSE-KMS','KmsKeyArn': <kms_arn>}]}",
-      "NativeIaC": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#cloudformation",
-      "Other": "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/job-bookmark-encryption-enabled.html",
-      "Terraform": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#terraform"
+      "CLI": "",
+      "NativeIaC": "```yaml\n# CloudFormation: Enable Job Bookmark encryption and attach to the Dev Endpoint\nResources:\n  GlueSecurityConfiguration:\n    Type: AWS::Glue::SecurityConfiguration\n    Properties:\n      Name: <example_resource_name>\n      EncryptionConfiguration:\n        JobBookmarksEncryption:\n          JobBookmarksEncryptionMode: CSE-KMS  # Critical: enables Job Bookmark encryption\n          KmsKeyArn: <example_kms_key_arn>     # Critical: KMS key used for Job Bookmark encryption\n\n  GlueDevEndpoint:\n    Type: AWS::Glue::DevEndpoint\n    Properties:\n      RoleArn: <example_role_arn>\n      SecurityConfiguration: !Ref GlueSecurityConfiguration  # Critical: attach the security configuration to the Dev Endpoint\n```",
+      "Other": "1. In the AWS Console, go to Glue > Security configurations > Add security configuration\n2. Enter a name, then under Advanced settings enable Job bookmark encryption and select a KMS key (or enter its ARN); Save\n3. Go to Glue > Dev endpoints\n4. Create a new Dev endpoint (or recreate the existing one) and set Security configuration to the configuration created in step 2\n5. Create the endpoint to apply the setting",
+      "Terraform": "```hcl\n# Terraform: Enable Job Bookmark encryption and attach to the Dev Endpoint\nresource \"aws_glue_security_configuration\" \"<example_resource_name>\" {\n  name = \"<example_resource_name>\"\n\n  encryption_configuration {\n    job_bookmarks_encryption {\n      job_bookmarks_encryption_mode = \"CSE-KMS\"   # Critical: enables Job Bookmark encryption\n      kms_key_arn                   = \"<example_kms_key_arn>\"  # Critical: KMS key used for Job Bookmark encryption\n    }\n  }\n}\n\nresource \"aws_glue_dev_endpoint\" \"<example_resource_name>\" {\n  name                   = \"<example_resource_name>\"\n  role_arn               = \"<example_role_arn>\"\n  security_configuration = aws_glue_security_configuration.<example_resource_name>.name  # Critical: attach the security configuration\n}\n```"
     },
     "Recommendation": {
-      "Text": "Enable Encryption in the Security configurations.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html"
+      "Text": "Attach a **security configuration** to each development endpoint and enable **job bookmark encryption** with a managed KMS key. Apply **least privilege** to S3 and KMS, rotate keys, and align logs and data stores with consistent encryption for **defense in depth**. Regularly audit endpoints for missing or outdated configurations.",
+      "Url": "https://hub.prowler.com/check/glue_development_endpoints_job_bookmark_encryption_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_development_endpoints_s3_encryption_enabled/glue_development_endpoints_s3_encryption_enabled.metadata.json

@@ -1,28 +1,34 @@
 {
   "Provider": "aws",
   "CheckID": "glue_development_endpoints_s3_encryption_enabled",
-  "CheckTitle": "Check if Glue development endpoints have S3 encryption enabled.",
+  "CheckTitle": "Glue development endpoint has S3 encryption enabled",
   "CheckType": [
+    "Software and Configuration Checks/AWS Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
     "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
+  "ResourceIdTemplate": "",
   "Severity": "medium",
   "ResourceType": "Other",
-  "Description": "Check if Glue development endpoints have S3 encryption enabled.",
-  "Risk": "Data exfiltration could happen if information is not protected. KMS keys provide additional security level to IAM policies.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/encryption-security-configuration.html",
+  "Description": "**AWS Glue development endpoints** are evaluated for an attached **security configuration** with **S3 encryption**. Endpoints lacking a security configuration, or with `s3_encryption` set to `DISABLED`, are flagged by this check.",
+  "Risk": "Unencrypted S3 writes from dev endpoints leave ETL outputs, temp data, and scripts readable at rest. A misconfigured bucket or stolen creds can expose sensitive content, harming **confidentiality** and triggering compliance issues.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/s3-encryption-enabled.html",
+    "https://docs.aws.amazon.com/glue/latest/dg/encryption-security-configuration.html"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue create-security-configuration --name s3-encrypted-sec-config --encryption-configuration {'S3Encryption': [{'S3EncryptionMode': 'SSE-KMS','KmsKeyArn': <kms_arn>}]}",
-      "NativeIaC": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#cloudformation",
-      "Other": "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/s3-encryption-enabled.html",
-      "Terraform": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#terraform"
+      "CLI": "",
+      "NativeIaC": "```yaml\n# CloudFormation: Glue Dev Endpoint with S3 encryption via Security Configuration\nResources:\n  SecurityConfig:\n    Type: AWS::Glue::SecurityConfiguration\n    Properties:\n      Name: <example_resource_name>\n      EncryptionConfiguration:\n        S3Encryptions:\n          - S3EncryptionMode: SSE-S3  # CRITICAL: enables S3 encryption for the security configuration\n\n  DevEndpoint:\n    Type: AWS::Glue::DevEndpoint\n    Properties:\n      EndpointName: <example_resource_name>\n      RoleArn: <example_role_arn>\n      SecurityConfiguration: !Ref SecurityConfig  # CRITICAL: attaches the encrypted security configuration to the dev endpoint\n```",
+      "Other": "1. In the AWS Console, go to AWS Glue > Security configurations > Create security configuration\n2. Under S3 encryption, select Server-side encryption (SSE-S3) and save\n3. Go to AWS Glue > Development endpoints > Create development endpoint\n4. Fill required fields and set Security configuration to the one created in step 2\n5. Create the endpoint and delete the old endpoint (without encryption) if it exists",
+      "Terraform": "```hcl\n# Terraform: Glue Dev Endpoint with S3 encryption\nresource \"aws_glue_security_configuration\" \"secure\" {\n  name = \"<example_resource_name>\"\n  encryption_configuration {\n    s3_encryption {\n      s3_encryption_mode = \"SSE-S3\"  # CRITICAL: enables S3 encryption\n    }\n  }\n}\n\nresource \"aws_glue_dev_endpoint\" \"dev\" {\n  name     = \"<example_resource_name>\"\n  role_arn = \"<example_role_arn>\"\n\n  security_configuration = aws_glue_security_configuration.secure.name  # CRITICAL: attaches encrypted security configuration\n}\n```"
     },
     "Recommendation": {
-      "Text": "Specify AWS KMS keys to use for input and output from S3 and EBS.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/encryption-security-configuration.html"
+      "Text": "Attach a **Glue security configuration** to each dev endpoint with **S3 encryption** enabled; prefer `SSE-KMS` with customer-managed keys. Enforce **least privilege** on IAM and KMS key policies, and extend encryption to logs and bookmarks for **defense in depth**.",
+      "Url": "https://hub.prowler.com/check/glue_development_endpoints_s3_encryption_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_etl_jobs_amazon_s3_encryption_enabled/glue_etl_jobs_amazon_s3_encryption_enabled.metadata.json

@@ -1,28 +1,35 @@
 {
   "Provider": "aws",
   "CheckID": "glue_etl_jobs_amazon_s3_encryption_enabled",
-  "CheckTitle": "Check if Glue ETL Jobs have S3 encryption enabled.",
+  "CheckTitle": "Glue job has S3 encryption enabled",
   "CheckType": [
-    "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
+    "Software and Configuration Checks/AWS Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark",
+    "Effects/Data Exposure"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
-  "Severity": "medium",
-  "ResourceType": "AwsGlueJob",
-  "Description": "Check if Glue ETL Jobs have S3 encryption enabled.",
-  "Risk": "If not enabled sensitive information at rest is not protected.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+  "ResourceIdTemplate": "",
+  "Severity": "high",
+  "ResourceType": "Other",
+  "Description": "**AWS Glue ETL jobs** are validated to use **Amazon S3 at-rest encryption** (`SSE-S3` or `SSE-KMS`) when writing outputs, either through an attached security configuration or via job arguments. Jobs missing a security configuration or with S3 encryption disabled are identified.",
+  "Risk": "Storing job outputs in S3 without **at-rest encryption** weakens **confidentiality**. Plaintext objects can be exposed via misconfigured bucket policies, compromised credentials, or media reuse, and lack **KMS key controls**, rotation, and audit trails-hindering incident response and compliance.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+    "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/s3-encryption-enabled.html"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue create-security-configuration --name s3-encrypted-sec-config --encryption-configuration {'S3Encryption': [{'S3EncryptionMode': 'SSE-KMS','KmsKeyArn': <kms_arn>}]}",
-      "NativeIaC": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#cloudformation",
-      "Other": "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/s3-encryption-enabled.html",
-      "Terraform": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#terraform"
+      "CLI": "",
+      "NativeIaC": "```yaml\n# CloudFormation: Attach a Security Configuration with S3 encryption to a Glue job\nResources:\n  GlueSecurityConfiguration:\n    Type: AWS::Glue::SecurityConfiguration\n    Properties:\n      Name: <example_resource_name>\n      EncryptionConfiguration:\n        S3Encryptions:\n          - S3EncryptionMode: SSE-S3  # CRITICAL: Enables S3 encryption for Glue outputs\n\n  GlueJob:\n    Type: AWS::Glue::Job\n    Properties:\n      Name: <example_resource_name>\n      Role: <example_role_arn>\n      Command:\n        Name: glueetl\n        ScriptLocation: s3://<example_resource_name>/script.py\n      SecurityConfiguration: !Ref GlueSecurityConfiguration  # CRITICAL: Applies encrypted security configuration to the job\n```",
+      "Other": "1. In the AWS Console, go to AWS Glue > Security configurations > Create security configuration\n2. Enable S3 encryption and choose SSE-S3 (or SSE-KMS with your key)\n3. Save the configuration\n4. Go to AWS Glue > Jobs > select your job > Edit\n5. Under Job details, set Security configuration to the encrypted configuration you created\n6. Save the job",
+      "Terraform": "```hcl\n# Terraform: Attach a Security Configuration with S3 encryption to a Glue job\nresource \"aws_glue_security_configuration\" \"sec\" {\n  name = \"<example_resource_name>\"\n\n  s3_encryption {\n    s3_encryption_mode = \"SSE-S3\"  # CRITICAL: Enables S3 encryption for Glue outputs\n  }\n}\n\nresource \"aws_glue_job\" \"job\" {\n  name     = \"<example_resource_name>\"\n  role_arn = \"<example_role_arn>\"\n\n  command {\n    script_location = \"s3://<example_resource_name>/script.py\"\n  }\n\n  security_configuration = aws_glue_security_configuration.sec.name  # CRITICAL: Applies encrypted security configuration to the job\n}\n```"
     },
     "Recommendation": {
-      "Text": "Provide the encryption properties that are used by crawlers, jobs and development endpoints.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html"
+      "Text": "Require **S3 encryption** for all Glue jobs via security configurations, preferring **SSE-KMS**. Apply **least privilege** to KMS keys, restrict key usage and rotate regularly. Enforce defense-in-depth with bucket policies that require encrypted writes, and monitor with key and S3 access logs.",
+      "Url": "https://hub.prowler.com/check/glue_etl_jobs_amazon_s3_encryption_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_etl_jobs_cloudwatch_logs_encryption_enabled/glue_etl_jobs_cloudwatch_logs_encryption_enabled.metadata.json

@@ -1,28 +1,35 @@
 {
   "Provider": "aws",
   "CheckID": "glue_etl_jobs_cloudwatch_logs_encryption_enabled",
-  "CheckTitle": "Check if Glue ETL Jobs have CloudWatch Logs encryption enabled.",
+  "CheckTitle": "Glue ETL job has CloudWatch Logs encryption enabled",
   "CheckType": [
-    "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
+    "Software and Configuration Checks/AWS Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark",
+    "Software and Configuration Checks/Industry and Regulatory Standards/NIST 800-53 Controls (USA)"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
+  "ResourceIdTemplate": "",
   "Severity": "medium",
   "ResourceType": "AwsGlueJob",
-  "Description": "Check if Glue ETL Jobs have CloudWatch Logs encryption enabled.",
-  "Risk": "If not enabled sensitive information at rest is not protected.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+  "Description": "**AWS Glue ETL jobs** are evaluated for a **security configuration** with **CloudWatch Logs encryption** (`SSE-KMS`) enabled. Jobs without a security configuration, or with CloudWatch Logs encryption set to `DISABLED`, are highlighted.",
+  "Risk": "Unencrypted Glue logs weaken **confidentiality**.\n\nLog entries can expose credentials, PII, connection strings, and schema details. Anyone with log storage access can harvest secrets for **lateral movement** and data exfiltration, widening the blast radius of compromises.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+    "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/cloud-watch-logs-encryption-enabled.html"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue create-security-configuration --name cw-encrypted-sec-config --encryption-configuration {'CloudWatchEncryption': [{'CloudWatchEncryptionMode': 'SSE-KMS','KmsKeyArn': <kms_arn>}]}",
-      "NativeIaC": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#cloudformation",
-      "Other": "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/cloud-watch-logs-encryption-enabled.html",
-      "Terraform": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#terraform"
+      "CLI": "",
+      "NativeIaC": "```yaml\n# CloudFormation: enable CloudWatch Logs encryption and attach to the job\nResources:\n  ExampleSecurityConfiguration:\n    Type: AWS::Glue::SecurityConfiguration\n    Properties:\n      Name: <example_resource_name>\n      EncryptionConfiguration:\n        CloudWatchEncryption:  # Critical: enable CloudWatch Logs encryption for Glue\n          CloudWatchEncryptionMode: SSE-KMS  # Critical: must not be DISABLED\n          KmsKeyArn: <example_kms_key_arn>   # Critical: KMS key used for encryption\n\n  ExampleJob:\n    Type: AWS::Glue::Job\n    Properties:\n      Role: <example_role_arn>\n      Command:\n        Name: glueetl\n        ScriptLocation: s3://<example_script_path>\n      SecurityConfiguration: !Ref ExampleSecurityConfiguration  # Critical: attach security configuration to the job\n```",
+      "Other": "1. In the AWS Glue console, go to Security configurations > Add security configuration\n2. Enter a name, enable CloudWatch Logs encryption, select SSE-KMS, and choose/provide the KMS key ARN; Save\n3. Go to Jobs, select the target job, click Edit\n4. Set Security configuration to the one created in step 2\n5. Save changes",
+      "Terraform": "```hcl\n# Enable CloudWatch Logs encryption and attach to the Glue job\nresource \"aws_glue_security_configuration\" \"example_resource_name\" {\n  name = \"<example_resource_name>\"\n\n  encryption_configuration {\n    cloudwatch_encryption {\n      cloudwatch_encryption_mode = \"SSE-KMS\"          # Critical: enable CW Logs encryption\n      kms_key_arn                = \"<example_kms_key_arn>\" # Critical: KMS key for encryption\n    }\n  }\n}\n\nresource \"aws_glue_job\" \"example_resource_name\" {\n  name     = \"<example_resource_name>\"\n  role_arn = \"<example_role_arn>\"\n\n  command {\n    name            = \"glueetl\"\n    script_location = \"s3://<example_script_path>\"\n  }\n\n  security_configuration = aws_glue_security_configuration.example_resource_name.name # Critical: attach security config to job\n}\n```"
     },
     "Recommendation": {
-      "Text": "Enable Encryption in the Security configurations.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html"
+      "Text": "Enable **at-rest encryption** for Glue logs via a **security configuration** using customer-managed KMS keys. Apply **least privilege** to KMS and CloudWatch Logs, rotate keys, and require all jobs to attach an approved configuration. Embed this baseline in IaC for consistent, **defense-in-depth** coverage.",
+      "Url": "https://hub.prowler.com/check/glue_etl_jobs_cloudwatch_logs_encryption_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_etl_jobs_job_bookmark_encryption_enabled/glue_etl_jobs_job_bookmark_encryption_enabled.metadata.json

@@ -1,28 +1,33 @@
 {
   "Provider": "aws",
   "CheckID": "glue_etl_jobs_job_bookmark_encryption_enabled",
-  "CheckTitle": "Check if Glue ETL Jobs have Job bookmark encryption enabled.",
+  "CheckTitle": "Glue ETL job has Job bookmark encryption enabled",
   "CheckType": [
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
     "Software and Configuration Checks/Industry and Regulatory Standards/CIS AWS Foundations Benchmark"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:certificate/resource-id",
+  "ResourceIdTemplate": "",
   "Severity": "medium",
-  "ResourceType": "AwsGlueJob",
-  "Description": "Check if Glue ETL Jobs have Job bookmark encryption enabled.",
-  "Risk": "If not enabled sensitive information at rest is not protected.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+  "ResourceType": "Other",
+  "Description": "**AWS Glue ETL jobs** should link a **security configuration** with **job bookmark encryption** enabled. Bookmark encryption must not be `DISABLED` (e.g., use `CSE-KMS`). Jobs lacking a security configuration are treated as not protecting bookmark metadata.",
+  "Risk": "Unencrypted **job bookmarks** in S3 expose execution state and data pointers, reducing **confidentiality**. Altered bookmarks can trigger reruns, skips, or reprocessing, harming **integrity**. Missing security configs may also leave logs and temporary objects unencrypted.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html",
+    "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/job-bookmark-encryption-enabled.html"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue create-security-configuration --name jb-encrypted-sec-config --encryption-configuration {'JobBookmarksEncryption': [{'JobBookmarksEncryptionMode': 'SSE-KMS','KmsKeyArn': <kms_arn>}]}",
-      "NativeIaC": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#cloudformation",
-      "Other": "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/Glue/job-bookmark-encryption-enabled.html",
-      "Terraform": "https://docs.prowler.com/checks/aws/general-policies/bc_aws_general_41#terraform"
+      "CLI": "",
+      "NativeIaC": "```yaml\n# CloudFormation: Enable Glue Job bookmark encryption via Security Configuration\nResources:\n  <example_resource_name>:\n    Type: AWS::Glue::SecurityConfiguration\n    Properties:\n      Name: <example_resource_name>\n      EncryptionConfiguration:\n        JobBookmarksEncryption:\n          JobBookmarksEncryptionMode: CSE-KMS  # CRITICAL: Enables job bookmark encryption\n          KmsKeyArn: <example_kms_key_arn>     # CRITICAL: KMS key used to encrypt job bookmarks\n```",
+      "Other": "1. In the AWS Console, go to AWS Glue > Security configurations > Add security configuration\n2. Enter a name and under Advanced settings enable Job bookmark encryption\n3. Select a KMS key (or paste the key ARN) and click Create\n4. Go to AWS Glue > Jobs, select the job, click Edit\n5. Under Advanced properties, set Security configuration to the one created above\n6. Click Save",
+      "Terraform": "```hcl\n# Terraform: Enable Glue Job bookmark encryption via Security Configuration\nresource \"aws_glue_security_configuration\" \"<example_resource_name>\" {\n  name = \"<example_resource_name>\"\n\n  encryption_configuration {\n    job_bookmarks_encryption {\n      job_bookmarks_encryption_mode = \"CSE-KMS\"      # CRITICAL: Enables job bookmark encryption\n      kms_key_arn                    = \"<example_kms_key_arn>\"  # CRITICAL: KMS key for bookmarks\n    }\n  }\n}\n```"
     },
     "Recommendation": {
-      "Text": "Enable Encryption in the Security configurations.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/console-security-configurations.html"
+      "Text": "Attach a **Glue security configuration** to every job and enable **job bookmark encryption** (e.g., `CSE-KMS`). Use **customer-managed KMS keys**, enforce **least privilege** on key usage, and rotate keys. For **defense in depth**, also encrypt **S3 temp data** and **CloudWatch logs** in the same configuration.",
+      "Url": "https://hub.prowler.com/check/glue_etl_jobs_job_bookmark_encryption_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_etl_jobs_logging_enabled/glue_etl_jobs_logging_enabled.metadata.json

@@ -1,28 +1,34 @@
 {
   "Provider": "aws",
   "CheckID": "glue_etl_jobs_logging_enabled",
-  "CheckTitle": "[DEPRECATED] Check if Glue ETL Jobs have logging enabled.",
+  "CheckTitle": "Glue ETL job has continuous CloudWatch logging enabled",
   "CheckType": [
+    "Software and Configuration Checks/AWS Security Best Practices/Runtime Behavior Analysis",
     "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices"
   ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:partition:glue:region:account-id:job/job-name",
+  "ResourceIdTemplate": "",
   "Severity": "medium",
-  "ResourceType": "AwsGlueJob",
-  "Description": "[DEPRECATED] Ensure that Glue ETL Jobs have CloudWatch logs enabled.",
-  "Risk": "Without logging enabled, AWS Glue jobs lack visibility into job activities and failures, making it difficult to detect unauthorized access, troubleshoot issues, and ensure compliance. This may result in untracked security incidents or operational issues that affect data processing.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/monitor-continuous-logging.html",
+  "ResourceType": "Other",
+  "Description": "**AWS Glue jobs** are assessed for **continuous CloudWatch logging**, confirming that runtime events and outputs are sent to **CloudWatch Logs** via the `--enable-continuous-cloudwatch-log` configuration.",
+  "Risk": "Missing job logs hide execution details and access patterns, enabling undetected credential abuse, data exfiltration in scripts, or tampering with transforms. This reduces confidentiality and integrity, hinders incident response, and can mask failures that impact availability.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/monitor-continuous-logging.html",
+    "https://docs.aws.amazon.com/glue/latest/dg/monitor-continuous-logging-enable.html",
+    "https://docs.aws.amazon.com/securityhub/latest/userguide/glue-controls.html#glue-2"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue update-job --job-name <job-name> --job-update \"Command={DefaultArguments={--enable-continuous-cloudwatch-log=true}}\"",
-      "NativeIaC": "",
-      "Other": "https://docs.aws.amazon.com/securityhub/latest/userguide/glue-controls.html#glue-2",
-      "Terraform": ""
+      "CLI": "aws glue update-job --job-name <example_resource_name> --job-update '{\"DefaultArguments\":{\"--enable-continuous-cloudwatch-log\":\"true\"}}'",
+      "NativeIaC": "```yaml\nResources:\n  GlueJob:\n    Type: AWS::Glue::Job\n    Properties:\n      Role: \"<example_resource_id>\"\n      Command:\n        Name: glueetl\n        ScriptLocation: \"s3://<example_resource_name>/script.py\"\n      DefaultArguments:\n        \"--enable-continuous-cloudwatch-log\": \"true\"  # Critical: enables continuous CloudWatch logging to pass the check\n```",
+      "Other": "1. Open the AWS Glue console and go to Jobs\n2. Select the job and click Edit\n3. Expand Advanced properties\n4. Under Continuous logging, check Enable logs in CloudWatch\n5. Save",
+      "Terraform": "```hcl\nresource \"aws_glue_job\" \"<example_resource_name>\" {\n  name     = \"<example_resource_name>\"\n  role_arn = \"<example_resource_id>\"\n\n  command {\n    script_location = \"s3://<example_resource_name>/script.py\"\n  }\n\n  default_arguments = {\n    \"--enable-continuous-cloudwatch-log\" = \"true\" # Critical: enables continuous CloudWatch logging to pass the check\n  }\n}\n```"
     },
     "Recommendation": {
-      "Text": "Enable logging for AWS Glue jobs to capture and monitor job events. Logging allows for better visibility into job performance, error detection, and security oversight.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/monitor-continuous-logging-enable.html"
+      "Text": "Enable **continuous logging** to **CloudWatch Logs** for all Glue jobs. Centralize logs with retention and KMS encryption, restrict read access, and alert on anomalies and failures. Apply **least privilege** to job roles and use **defense in depth** by correlating logs across services.",
+      "Url": "https://hub.prowler.com/check/glue_etl_jobs_logging_enabled"
     }
   },
   "Categories": [

prowler/providers/aws/services/glue/glue_ml_transform_encrypted_at_rest/glue_ml_transform_encrypted_at_rest.metadata.json

@@ -1,26 +1,34 @@
 {
   "Provider": "aws",
   "CheckID": "glue_ml_transform_encrypted_at_rest",
-  "CheckTitle": "Check if Glue ML Transform Encryption at Rest is Enabled",
-  "CheckType": [],
+  "CheckTitle": "Glue ML Transform is encrypted at rest",
+  "CheckType": [
+    "Software and Configuration Checks/AWS Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/AWS Foundational Security Best Practices",
+    "Software and Configuration Checks/Industry and Regulatory Standards/NIST 800-53 Controls (USA)"
+  ],
   "ServiceName": "glue",
   "SubServiceName": "",
-  "ResourceIdTemplate": "arn:aws:glue:region:account-id:mlTransform/transform-id",
+  "ResourceIdTemplate": "",
   "Severity": "medium",
   "ResourceType": "Other",
-  "Description": "This control checks whether an AWS Glue machine learning transform is encrypted at rest. The control fails if the machine learning transform isn't encrypted at rest.",
-  "Risk": "Data at rest refers to data that's stored in persistent, non-volatile storage for any duration. Encrypting data at rest helps you protect its confidentiality, which reduces the risk that an unauthorized user can access it.",
-  "RelatedUrl": "https://docs.aws.amazon.com/glue/latest/dg/encryption-at-rest.html",
+  "Description": "**AWS Glue ML transforms** are evaluated for **encryption at rest** of transform user data using **KMS keys**. The finding highlights transforms where encryption is not configured.",
+  "Risk": "Without encryption, **confidentiality** is weakened: transform artifacts, mappings, and sample datasets may be readable via storage access, backups, or cross-account exposure. This can lead to data disclosure and aid **lateral movement** by revealing schemas and data relationships.",
+  "RelatedUrl": "",
+  "AdditionalURLs": [
+    "https://docs.aws.amazon.com/glue/latest/dg/encryption-at-rest.html",
+    "https://docs.aws.amazon.com/securityhub/latest/userguide/glue-controls.html#glue-3"
+  ],
   "Remediation": {
     "Code": {
-      "CLI": "aws glue update-ml-transform --transform-id <transform-id> --encryption-at-rest {\"Enabled\":true,\"KmsKey\":\"<kms-key-arn>\"}",
-      "NativeIaC": "",
-      "Other": "https://docs.aws.amazon.com/securityhub/latest/userguide/glue-controls.html#glue-3",
-      "Terraform": ""
+      "CLI": "aws glue update-ml-transform --transform-id <transform-id> --transform-encryption '{\"MlUserDataEncryption\":{\"MlUserDataEncryptionMode\":\"SSE-KMS\",\"KmsKeyId\":\"<kms-key-arn>\"}}'",
+      "NativeIaC": "```yaml\nResources:\n  <example_resource_name>:\n    Type: AWS::Glue::MLTransform\n    Properties:\n      Role: <example_resource_id>\n      InputRecordTables:\n        - DatabaseName: <example_resource_name>\n          TableName: <example_resource_name>\n      TransformParameters:\n        TransformType: FIND_MATCHES\n        FindMatchesParameters:\n          PrimaryKeyColumnName: <example_resource_name>\n      TransformEncryption:\n        MlUserDataEncryption:\n          MlUserDataEncryptionMode: SSE-KMS  # Critical: enables ML user data encryption at rest\n          KmsKeyId: <kms-key-arn>            # Critical: KMS key used for encryption\n```",
+      "Other": "1. In the AWS Management Console, open AWS Glue\n2. Go to Machine learning > Transforms and select the target transform\n3. Click Edit\n4. Under Encryption, enable ML user data encryption\n5. Choose an AWS KMS key\n6. Save changes",
+      "Terraform": "```hcl\nresource \"aws_glue_ml_transform\" \"<example_resource_name>\" {\n  name     = \"<example_resource_name>\"\n  role_arn = \"<example_resource_id>\"\n\n  input_record_tables {\n    database_name = \"<example_resource_name>\"\n    table_name    = \"<example_resource_name>\"\n  }\n\n  parameters {\n    transform_type = \"FIND_MATCHES\"\n    find_matches_parameters {\n      primary_key_column_name = \"<example_resource_name>\"\n    }\n  }\n\n  transform_encryption {\n    ml_user_data_encryption {\n      ml_user_data_encryption_mode = \"SSE-KMS\"   # Critical: enables encryption at rest\n      kms_key_id                   = \"<kms-key-arn>\" # Critical: KMS key used for encryption\n    }\n  }\n}\n```"
     },
     "Recommendation": {
-      "Text": "Enable encryption at rest for Glue ML Transforms using AWS KMS keys.",
-      "Url": "https://docs.aws.amazon.com/glue/latest/dg/encryption-at-rest.html"
+      "Text": "Enable **KMS-backed encryption at rest** for all ML transforms and prefer **customer-managed keys**.\n- Apply **least privilege** key policies and rotate keys\n- Enforce **defense in depth** with network and IAM controls\n- Monitor key usage and transform access with audit logs",
+      "Url": "https://hub.prowler.com/check/glue_ml_transform_encrypted_at_rest"
     }
   },
   "Categories": [

prowler/providers/aws/services/iam/iam_inline_policy_allows_privilege_escalation/iam_inline_policy_allows_privilege_escalation.metadata.json

@@ -26,7 +26,9 @@
       "Url": "https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html#grant-least-privilege"
     }
   },
-  "Categories": [],
+  "Categories": [
+    "privilege-escalation"
+  ],
   "DependsOn": [],
   "RelatedTo": [],
   "Notes": ""

prowler/providers/aws/services/iam/iam_policy_allows_privilege_escalation/iam_policy_allows_privilege_escalation.metadata.json

@@ -27,7 +27,9 @@
       "Url": "https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html#grant-least-privilege"
     }
   },
-  "Categories": [],
+  "Categories": [
+    "privilege-escalation"
+  ],
   "DependsOn": [],
   "RelatedTo": [],
   "Notes": "CAF Security Epic: IAM"

prowler/providers/aws/services/iam/iam_policy_cloudshell_admin_not_attached/iam_policy_cloudshell_admin_not_attached.metadata.json

@@ -26,7 +26,7 @@
     }
   },
   "Categories": [
-    "trustboundaries"
+    "trust-boundaries"
   ],
   "DependsOn": [],
   "RelatedTo": [],