MCP App Store
by KeenEthics
Prowler Cloud for Claude Code icon

Prowler Cloud for Claude Code MCP Server for Claude

By ProwlerPro Inc.

Overview

Prowler Cloud security and compliance skills for Claude Code, powered by the Prowler MCP server. Triage compliance gaps and remediate findings on AWS, Azure, GCP, Kubernetes, Microsoft 365, GitHub and many more providers listed at https://registry.prowler.com, plus custom providers, until your account meets the framework you choose.

How to connect

  1. Claude: Open the Prowler Cloud for Claude Code listing in the Claude connectors directory and choose Connect. Claude listing Prowler Cloud for Claude Code exposes 100 tools here.

Tools

prowler_cloud_apply_organization_discovery

Claude
Apply a succeeded discovery: create/link Prowler providers for the selected accounts, subscriptions or projects and build the OU/management-group/folder hierarchy. For AWS organizations, pass the accounts to onboard. Onboarding the ENTIRE organization (every discovered account) requires all_accounts=true, so confirm that with the user first. For Azure, subscriptions is required and must be non-empty; for GCP, projects is required and must be non-empty. Items whose discovery apply_status was 'blocked' (e.g. the account already belongs to another organization) will be rejected by the API. Requires the manage_providers permission on the API key/role.

prowler_cloud_build_alert_rule_condition

Claude
Build and dry-run an alert-rule condition in one call. Nothing is persisted. This combines the two preparation steps for an alert rule: 1. SEED: translate a findings filter_bag into a condition DSL (skipped when you pass a condition directly). 2. PREVIEW: dry-run that condition against the latest scan data. Returns the ready-to-use condition (pass it straight to prowler_cloud_create_alert_rule / prowler_cloud_update_alert_rule) alongside: - warnings: filters dropped during seeding (empty when a condition was passed in). - would_fire: whether the condition would have fired against the latest data. - evaluation_failed / last_error: whether the dry-run itself failed and why. - summary, duration_ms: supporting evaluation metadata. Provide exactly one of filter_bag or condition.

prowler_cloud_bulk_set_scan_schedules

Claude
Apply one scan schedule to MANY providers at once. This applies one COMPLETE schedule (scan_frequency + scan_hour required) and returns 'updated'/'failed' provider ids, not the schedule itself. For a single provider, or to make a partial edit such as pausing, use prowler_cloud_set_scan_schedule instead. Provide EITHER provider_ids OR provider_group_id (not both). Each provider is applied in its own transaction; the result reports 'updated' provider ids and 'failed' entries individually. Requires the manage_scans permission.

prowler_cloud_create_alert_recipient

Claude
Register a new alert recipient email. SIDE EFFECT: this enqueues a confirmation email to the address. Requires the manage_alerts permission on the API key/role.

prowler_cloud_create_alert_rule

Claude
Create a tenant-scoped alert rule. SIDE EFFECT: recipients that are not yet confirmed will receive a confirmation email. Requires the manage_alerts permission on the API key/role. Workflow: 1. Use prowler_cloud_build_alert_rule_condition to turn a findings filter into a validated, dry-run condition (returns the 'condition' plus any dropped-filter warnings). 2. Use this tool with that 'condition' to persist the rule.

prowler_cloud_create_finding_triage_note

Claude
Add a new note to a finding's triage. A finding's triage can hold multiple notes. To edit an existing note use prowler_cloud_update_finding_triage_note; to remove one use prowler_cloud_delete_finding_triage_note. Requires the manage_scans permission on the API key/role.

prowler_cloud_create_organization

Claude
Register a cloud provider organization in Prowler, optionally storing its org-level credentials in the same call. Credentials are required before discovery can run, so providing them here is recommended. Idempotent: if an organization with the same org_type and external_id already exists (e.g. from an earlier onboarding attempt), it is reused instead of failing with a duplicate error — its credentials are then created or rotated — and the response reports created: false. IMPORTANT for AWS: discovery assumes an IAM role that must already be deployed via Prowler's CloudFormation template — it creates the ProwlerScan role plus a StackSet that rolls it out to the member accounts, trusting your Prowler tenant id as the ExternalId. When this tool is called without credentials for an AWS organization, the response includes an aws_role_deployment guide (external id, template and quick-create link) to relay to the user; collect the deployed role's ARN afterwards and store it with prowler_cloud_update_organization. For Azure, external_id is the Azure tenant id (a UUID); the tenant-root management group is derived from it automatically. Workflow: 1. This tool (with secret_type + credentials) 2. prowler_cloud_discover_organization to enumerate accounts/subscriptions/projects 3. prowler_cloud_apply_organization_discovery to onboard them as providers Requires the manage_providers permission on the API key/role. Example Input: - AWS (external_id is filled with your Prowler tenant id automatically): ``json {"name": "Acme Org", "org_type": "aws", "external_id": "o-abc123def4", "secret_type": "role", "credentials": {"role_arn": "arn:aws:iam::123456789012:role/ProwlerScan"}} ` - Azure with a service principal (external_id is the Azure tenant id): `json {"name": "Acme Azure", "org_type": "azure", "external_id": "00000000-0000-0000-0000-000000000000", "secret_type": "static", "credentials": {"client_id": "11111111-1111-1111-1111-111111111111", "client_secret": "..."}} ` - GCP with a service account: `json {"name": "Acme GCP", "org_type": "gcp", "external_id": "123456789012", "secret_type": "service_account", "credentials": {"service_account_key": {"type": "service_account", "...": "..."}}} ``

prowler_cloud_create_scan_configuration

Claude
Create a scan configuration and optionally attach it to providers. Returns the stored configuration as saved, including its full body and the providers it ended up attached to. Workflow: 1. Use prowler_cloud_get_scan_configuration_schema to learn the valid configuration structure. 2. Use prowler_app_search_providers to find provider ids. 3. Use this tool to create and attach the configuration.

prowler_cloud_delete_alert_recipient

Claude
Delete an alert recipient. WARNING: This is a destructive operation. The recipient stops receiving alerts; past alert events that referenced it remain queryable. Requires manage_alerts.

prowler_cloud_delete_alert_rule

Claude
Delete an alert rule. WARNING: This is a destructive operation. The rule stops firing immediately; past alert events remain queryable. Requires the manage_alerts permission.

prowler_cloud_delete_finding_triage_note

Claude
Delete a note from a finding's triage. WARNING: This permanently removes the note and cannot be undone. Requires the manage_scans permission on the API key/role.

prowler_cloud_delete_organization

Claude
Start deleting an organization. WARNING: This is a destructive operation. It deletes the organization, its entire OU/folder hierarchy, and marks EVERY linked provider as deleted — removing their scans and findings. It cannot be undone. To detach providers without deleting them, use prowler_cloud_manage_organization_providers first. IMPORTANT: the API task this waits on only marks the organization deleted and dispatches one deletion job per linked provider; the organization row itself is removed by a follow-up job once every provider finishes, and a failure there rolls the whole deletion back. A successful call therefore means "deletion started, organization no longer visible", not "everything is gone" — report it that way, and confirm later with prowler_cloud_list_organizations. Requires the manage_providers permission on the API key/role. The result reports status: 'deletion_started' when Prowler accepted the deletion and began it, 'unknown' when it was accepted but its progress could not be read. NEVER send the deletion again on 'unknown' — use prowler_cloud_list_organizations to see whether the organization is gone.

prowler_cloud_delete_scan_configuration

Claude
Delete a scan configuration. WARNING: This is a destructive operation. Any providers currently attached to this configuration will fall back to the built-in default scan configuration.

prowler_cloud_delete_scan_schedule

Claude
Delete a provider's scan schedule. WARNING: This is a destructive operation - it stops recurring scans and resets the scan schedule to its unconfigured defaults. To temporarily stop scans instead, prefer prowler_cloud_set_scan_schedule with scan_enabled=False. Requires the manage_scans permission on the API key/role.

prowler_cloud_discover_organization

Claude
Discover the real structure of a cloud provider organization: AWS accounts and OUs, Azure subscriptions and management groups, or GCP projects and folders. Starts a discovery run (or checks an existing one when discovery_id is given) and waits up to wait_seconds for it to finish. On success it returns the discovered accounts/OUs (AWS), subscriptions/management groups (Azure) or projects/folders (GCP), each account, subscription or project with its registration state (provider_exists, apply_status, blocked_reasons) so you can choose what to onboard. If still running after the wait, it returns the discovery id and status — call this tool again with that discovery_id to keep waiting. IMPORTANT: requires org-level credentials to be stored first (see prowler_cloud_create_organization / prowler_cloud_update_organization). Workflow: 1. This tool 2. Review the returned accounts/subscriptions/projects 3. prowler_cloud_apply_organization_discovery with your selection Requires the manage_providers permission on the API key/role.

prowler_cloud_get_alert_event

Claude
Retrieve a single alert event including its matched rule and scan.

prowler_cloud_get_alert_recipient

Claude
Retrieve a single alert recipient with its confirmation status.

prowler_cloud_get_alert_rule

Claude
Retrieve an alert rule including its condition DSL and recipient emails.

prowler_cloud_get_finding_triage

Claude
Retrieve a single finding's triage state by finding UID.

prowler_cloud_get_organization

Claude
Get one organization in full: attributes, linked providers, credentials status, latest discovery and the OU/management-group/folder hierarchy. The credentials field only reports whether org-level credentials are stored and their type — secret values are write-only and never returned. latest_discovery carries counts and status only; for the discovered account/project lists use prowler_cloud_discover_organization with the discovery id.

prowler_cloud_get_scan_configuration

Claude
Retrieve a scan configuration including its full configuration body. The 'configuration' body follows the JSON Schema returned by prowler_cloud_get_scan_configuration_schema (one section per provider type).

prowler_cloud_get_scan_configuration_schema

Claude
Describe the keys a valid scan configuration body may set. Returns a compact, per-provider view (one section per provider type) of the configurable keys and their types/constraints. Use it to build the 'configuration' argument for prowler_cloud_create_scan_configuration or prowler_cloud_update_scan_configuration. HOW A SCAN CONFIGURATION BODY IS STRUCTURED The 'configuration' is a two-level mapping: PROVIDER TYPE -> (SETTING KEY -> VALUE). Each top-level key is a provider type ('aws', 'azure', ...); its value is that provider's settings. Example: { "aws": {"excluded_services": ["macie"], "max_ec2_instance_age_in_days": 180}, "azure": {"excluded_services": ["defender"]} } Everything is OPTIONAL and behaves as an OVERRIDE on top of Prowler's built-in defaults, never a full replacement: - Include only the provider types you want to tune; any provider type you omit keeps using its defaults. - Within a section, include only the keys you want to change; any key you omit keeps its default value at scan time. - A partial body is valid and preferred - even a single key for a single provider. You do NOT need to send every provider or every key, and you should not pad the body with defaults you are not intentionally changing. HOW TO READ EACH KEY IN THE RETURNED SCHEMA The response is {"providers": {<provider_type>: {"description": <text>, "fields": {<key>: <spec>}}}}. Each <spec> describes one settable key: - "type": JSON type to send - 'integer', 'number', 'boolean', 'string' or 'array'. - "description": what the setting controls. - "enum": when present, the value MUST be one of these; "minimum"/"maximum" are inclusive numeric bounds; "max_length" caps string length. - For arrays: "items_type" is the element type and "items_enum" (when present) is the closed set of allowed elements. "unique_items" (when true) means duplicate elements are rejected; "items_min_length" is the minimum length of each string element (1 means empty strings are rejected). - A missing constraint means "unconstrained"; a missing "default" means the key is unset (null) by default. Two keys recur across most providers: "excluded_checks" and "excluded_services" (lists of check / service identifiers to skip during the scan). Their values are validated against the provider's real catalog - discover valid identifiers with prowler_hub_list_checks and prowler_hub_get_provider_services. Pass provider_type to narrow the result to just that provider's section instead of every provider type. An unknown provider type fails with a message listing the valid ones.

prowler_cloud_get_scan_schedule

Claude
Retrieve a provider's scan schedule including all per-frequency fields.

prowler_cloud_list_alert_events

Claude
List fired alert events for the tenant.

prowler_cloud_list_alert_recipients

Claude
List alert recipients and their confirmation status.

prowler_cloud_list_alert_rule_events

Claude
List the fired alert-event history for a single rule (newest first).

prowler_cloud_list_alert_rules

Claude
List and filter custom alert rules. IMPORTANT: returns LIGHTWEIGHT rule info without the condition DSL or recipient emails. Use prowler_cloud_get_alert_rule for the full rule.

prowler_cloud_list_finding_triage_notes

Claude
List the notes attached to a finding's triage, newest first.

prowler_cloud_list_finding_triages

Claude
List and filter persisted finding triage rows for the tenant. Each row surfaces the triage 'id', finding_uid, check_id, status, notes_count and the owning provider. Use prowler_cloud_get_finding_triage (by finding UID) for a single finding's state, and prowler_cloud_list_finding_triage_notes to read its notes.

prowler_cloud_list_organizations

Claude
List cloud provider organizations registered in Prowler. IMPORTANT: returns LIGHTWEIGHT info per organization (name, type, external id, provider/node counts). Use prowler_cloud_get_organization for the hierarchy, credentials status and latest discovery.

prowler_cloud_list_scan_configurations

Claude
List and filter per-tenant scan configurations. IMPORTANT: This tool returns LIGHTWEIGHT scan configuration information (id, name, attached providers summary, timestamps) WITHOUT the full configuration body. Use prowler_cloud_get_scan_configuration to fetch the complete configuration for a specific entry. Workflow: 1. Use this tool to browse existing scan configurations. 2. Use prowler_cloud_get_scan_configuration with the 'id' for the full body. 3. Use prowler_cloud_create_scan_configuration / prowler_cloud_update_scan_configuration to manage them.

prowler_cloud_list_scan_schedules

Claude
List scan schedules, one per visible provider. IMPORTANT: returns LIGHTWEIGHT scan schedule info (provider_id, frequency, enabled, next/last run). Use prowler_cloud_get_scan_schedule for the full per-frequency fields.

prowler_cloud_manage_organization_providers

Claude
Manually adjust which providers belong to an organization, or to one hierarchy node (OU/management group/folder) within it. IMPORTANT: prowler_cloud_apply_organization_discovery links providers automatically — use this tool only for manual adjustments. A provider can belong to at most ONE organization and ONE node; its type must match the organization's (409 conflict otherwise). Removing a provider from the organization also removes it from any node. Providers are detached, never deleted. Requires the manage_providers permission on the API key/role.

prowler_cloud_resend_alert_recipient_confirmation

Claude
Re-send the confirmation email for a pending or unsubscribed recipient. SIDE EFFECT: sends an email. Requires the manage_alerts permission.

prowler_cloud_set_finding_triage_status

Claude
Set the triage status for a finding, optionally attaching a note. Requires the manage_scans permission on the API key/role. Workflow: 1. Use prowler_cloud_get_finding_triage to review the current state. 2. Use this tool to change status (e.g. mark a finding 'risk_accepted'). 3. Use prowler_cloud_create_finding_triage_note to add follow-up notes.

prowler_cloud_set_scan_schedule

Claude
Configure or update a SINGLE provider's recurring scan schedule. Supports partial edits (e.g. pass only scan_enabled=False to pause) and returns the full resulting schedule. Cadence fields not used by the chosen frequency are cleared automatically, so switching frequency is safe. To pause instead of deleting, set scan_enabled=False. To apply one schedule to many providers or a whole group at once, use prowler_cloud_bulk_set_scan_schedules instead. Requires the manage_scans permission on the API key/role.

prowler_cloud_update_alert_rule

Claude
Update an alert rule. Only provided fields change. Requires the manage_alerts permission. Changing recipients may send new confirmation emails.

prowler_cloud_update_finding_triage_note

Claude
Update the body of an existing note on a finding's triage. To add a new note instead use prowler_cloud_create_finding_triage_note; to remove one use prowler_cloud_delete_finding_triage_note. Requires the manage_scans permission on the API key/role.

prowler_cloud_update_organization

Claude
Update an organization's name or metadata, and/or create or rotate its org-level credentials. IMPORTANT: org_type and external_id are immutable after creation. With no arguments this returns the current organization unchanged. The attribute update and the credential write are separate API calls, so a rejected credential payload can leave the name/metadata change already applied. That case returns status: 'partial' with updated_fields and credentials_error — relay it instead of assuming nothing changed. Requires the manage_providers permission on the API key/role.

prowler_cloud_update_scan_configuration

Claude
Update a scan configuration's name, body, and/or attached providers. IMPORTANT: provider_ids is a full replacement set, not additive. Omitting it leaves attachments unchanged; passing it detaches any provider not listed. Returns the stored configuration as saved, including its full body and the providers it ended up attached to - check it to confirm the resulting attachments.

prowler_connect_provider

Claude
Register a provider to be scanned with Prowler. This tool will register a provider in Prowler, even if the UID is wrong. If the provider is already registered, it will be updated with the new provided alias or credentials if provided. If credentials are provided, they will be added to the indicated provider, if the provider does not exist, it will be created and the credentials will be added to it. If the connection test is successful, the provider will be connected. If the connection test fails, the provider will be created but not connected. The tool always returns the provider details after its registration or update. Example Input: - AWS Static Credentials: ``json { "provider_uid": "123456789012", "provider_type": "aws", "alias": "production-aws-account", "credentials": { "aws_access_key_id": "AKIA...", "aws_secret_access_key": "...", "aws_session_token": "..." } } ` - AWS Assume Role: `json { "provider_uid": "987654321098", "provider_type": "aws", "alias": "staging-aws-account", "credentials": { "role_arn": "arn:aws:iam::987654321098:role/ProwlerScanRole", "external_id": "...", "aws_access_key_id": "AKIA...", Optional "aws_secret_access_key": "...", Optional "aws_session_token": "...", Optional "session_duration": 3600, Optional "role_session_name": "..." Optional } } ` - Azure/M365 Static Credentials: `json { "provider_uid": "a1b2c3d4-e5f6-4a5b-8c9d-0e1f2a3b4c5d", "provider_type": "azure", "alias": "production-azure-subscription", "credentials": { "client_id": "...", "client_secret": "...", "tenant_id": "..." } } ` - GCP Service Account Account Key: `json { "provider_uid": "my-gcp-project-prod", "provider_type": "gcp", "alias": "production-gcp-project", "credentials": { "service_account_key": { "type": "service_account", "project_id": "...", "private_key_id": "...", "private_key": "...", "client_email": "...", } } } ` - Kubernetes Static Credentials: `json { "provider_uid": "prod-k8s-cluster", "provider_type": "kubernetes", "alias": "production-kubernetes-cluster", "credentials": { "kubeconfig_content": "..." } } ` - GitHub OAuth App Token: ``json { "provider_uid": "my-organization", "provider_type": "github", "alias": "my-github-organization", "credentials": { "oauth_app_token": "..." } } NOTE: THERE ARE MORE PROVIDER TYPES AND CREDENTIAL TYPES AVAILABLE, PLEASE REFER TO THE Prowler Hub/Prowler Documentation that you can also find in form of tools in this MCP Server.

prowler_create_amazon_s3_integration

Claude
Create an Amazon S3 integration to export scan outputs to an S3 bucket. After every scan of an attached provider, Prowler uploads the generated reports to 's3://{bucket_name}/{output_directory}/'. IMPORTANT: The connection is checked right after creation, and the result is part of the response. The check writes and deletes a small test object in the bucket, so the credentials need s3:PutObject, s3:ListBucket and s3:DeleteObject on it. Default behavior: - The integration is created enabled - All credential parameters are optional: providing none sends empty credentials, which makes Prowler use the ambient AWS credentials of the deployment. That only works on self-hosted Prowler, Prowler Cloud requires a role or static keys Example Input: - IAM role (recommended): ``json { "bucket_name": "my-security-reports", "output_directory": "prowler", "provider_ids": ["019ac0d6-90d5-73e9-9acf-c22e256f1bac"], "role_arn": "arn:aws:iam::123456789012:role/ProwlerS3Integration", "external_id": "019ac0d6-90d5-73e9-9acf-c22e256f1bac" } ` - Static credentials: `json { "bucket_name": "my-security-reports", "aws_access_key_id": "AKIA...", "aws_secret_access_key": "..." } `` Workflow: 1. Use prowler_search_providers to get the provider UUIDs to attach 2. Use this tool to create the integration 3. Read 'connected' in the response. If it is 'failed', read 'error', then fix the bucket policy or the credentials with prowler_update_integration

prowler_create_aws_security_hub_integration

Claude
Create an AWS Security Hub integration to send findings to Security Hub in ASFF format. After every scan of the attached provider, Prowler pushes its findings to Security Hub in every region where the Prowler partner integration is enabled. IMPORTANT: The Prowler integration must be enabled in AWS Security Hub beforehand, in each region where findings should land. The connection check performed right after creation is what discovers those regions and fills 'enabled_regions'. Default behavior: - The integration is created enabled - Leaving every credential parameter empty makes Prowler reuse the credentials already stored for the provider. This is the recommended setup - send_only_fails defaults to false, so passed findings are sent too Constraints: - Exactly one provider, and it must be an AWS provider - A provider can only have one Security Hub integration. Creating a second one fails with a conflict error Workflow: 1. Use prowler_search_providers with provider_type=['aws'] to get the provider UUID 2. Use this tool to create the integration 3. Read 'enabled_regions' in the response configuration. If it is empty, the Prowler integration is not enabled in Security Hub yet

prowler_create_jira_integration

Claude
Create a Jira integration to open Jira work items from Prowler findings. Unlike the other integration types, Jira is tenant-wide: it is not attached to any provider and applies to every finding the role can see. IMPORTANT: Jira integrations do not send anything automatically. Work items are only created on demand with prowler_send_findings_to_jira. IMPORTANT: The connection is checked right after creation, and that check is what discovers the available Jira projects. If 'connected' comes back 'failed', the 'projects' mapping stays empty and no finding can be dispatched. Default behavior: - The integration is created enabled - The configuration is entirely server-generated: 'domain', 'projects' and 'issue_types' Example Input: ``json { "domain": "acme", "user_mail": "security@acme.com", "api_token": "ATATT3xFfGF0..." } `` Workflow: 1. Use this tool to create the integration 2. Read 'projects' in the response configuration to pick a project key 3. Use prowler_get_jira_issue_types with that project key to pick an issue type 4. Use prowler_send_findings_to_jira to create the work items

prowler_create_mute_rule

Claude
Create a new mute rule to mute specific findings with documentation and audit trail. IMPORTANT: This immediately mutes the specified findings AND all previous findings with matching UIDs (this could take some time to complete). The rule is enabled by default. Muting is permanent. Default behavior: - Rule is created in enabled state - Applies to current and previous findings with matching UIDs - Records creator for audit trail The mute rule includes: - Core identification: id (UUID for prowler_get_mute_rule), name, reason - Configuration: enabled status, finding_uids list - Audit trail: user_creator_id (UUID of the Prowler user from the tenant that created the rule), timestamps when the rule was created and last modified Workflow: 1. Use prowler_search_security_findings to identify findings to mute 2. Use this tool with finding IDs, descriptive name, and documented reason 3. Verify with prowler_get_mute_rule to confirm rule creation 4. Check findings are muted with prowler_search_security_findings (filter by muted=true)

prowler_delete_integration

Claude
Permanently remove an integration from Prowler. WARNING: This is a destructive operation that cannot be undone. The stored credentials are destroyed with it, so the integration has to be recreated from scratch, with its credentials, to be used again. Deletion behavior: - Prowler stops sending results to this destination immediately - Data already exported stays where it is: objects in S3, findings in Security Hub and work items in Jira are not removed - To pause an integration instead, use prowler_update_integration with enabled=False Workflow: 1. Use prowler_get_integration to review what will be deleted 2. Use this tool to permanently remove it 3. Verify with prowler_list_integrations (it should no longer appear)

prowler_delete_mute_rule

Claude
Delete a mute rule from the system. WARNING: Findings that were muted by this rule REMAIN MUTED after deletion. This only removes the rule itself from management, not the muting effect on findings. The muted findings will stay muted permanently. Deletion behavior: - Rule is permanently removed from the system - Muted findings remain muted (deletion doesn't un-mute them) - Cannot be undone - rule must be recreated to restore Workflow: 1. Use prowler_get_mute_rule to review what will be deleted 2. Use this tool to permanently remove the rule 3. Verify deletion with prowler_list_mute_rules (rule should no longer appear)

prowler_delete_mutelist

Claude
Remove the mutelist configuration from the tenant. WARNING: This is a destructive operation that cannot be undone. - The mutelist will need to be re-created with prowler_set_mutelist - New findings from future scans will NOT be muted by the deleted mutelist - Previously muted findings remain muted (deletion doesn't un-mute them) Workflow: 1. Use prowler_get_mutelist to confirm what will be deleted 2. Use this tool to permanently remove the mutelist 3. New scans will no longer apply mutelist-based muting

prowler_delete_provider

Claude
Permanently remove a registered provider from Prowler. WARNING: This is a destructive operation that cannot be undone. The provider will need to be re-added with prowler_connect_provider if you want to scan it again. Prowler removes the provider and everything attached to it (its scans, findings and resources) in a background task, so a large provider can take longer than the time this tool waits for it. The result includes: - status: 'deleted' when Prowler finished removing the provider, 'in_progress' when the deletion was accepted and is still running - task_id: the background task, present when the deletion was still running NEVER send the deletion again while status='in_progress'. Use prowler_search_providers to check whether the provider is gone.

prowler_docs_get_document

Claude
Retrieve the full content of a Prowler documentation file. Use this after searching to get the complete content of a specific documentation file. Returns: Full content of the documentation file in markdown format.

prowler_get_attack_paths_cartography_schema

Claude
Retrieve the Cartography graph schema for a completed attack paths scan. This tool fetches the full Cartography schema (node labels, relationships, and properties) so the LLM can write accurate custom openCypher queries for attack paths analysis. Two-step flow: 1. Calls the Prowler API to get schema metadata (provider, version, URLs) 2. Fetches the raw Cartography schema markdown from GitHub Returns: - id: Schema resource identifier - provider: Cloud provider type - cartography_version: Schema version - schema_url: GitHub page URL for reference - raw_schema_url: Raw markdown URL - schema_content: Full Cartography schema markdown with node/relationship definitions Workflow: 1. Use prowler_list_attack_paths_scans to find a completed scan 2. Use this tool to get the schema for the scan's provider 3. Use the schema to craft custom openCypher queries 4. Execute queries with prowler_run_attack_paths_query

prowler_get_compliance_framework_state_details

Claude
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_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_get_finding_details with these finding IDs for more details and remediation guidance Default behavior: - Requires exactly one of scan_id OR provider_id; providing both is rejected - With provider_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_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_get_finding_details with the finding IDs to get remediation guidance

prowler_get_compliance_overview

Claude
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_get_compliance_framework_state_details with a specific compliance_id to see which requirements failed

prowler_get_current_user

Claude
Identify which user the current credentials authenticate as. Use this to determine the identity behind the credentials this MCP server is currently using, e.g. before performing actions on behalf of that user or when reporting who is connected. Returns the same detailed information as prowler_get_user: - id, name, email, company_name - date_joined, is_verified - role_ids, membership_ids

prowler_get_finding_details

Claude
Retrieve comprehensive details about a specific security finding by its ID. IMPORTANT: This tool returns COMPLETE finding details. Use this after finding a specific finding via prowler_search_security_findings This tool provides ALL information that prowler_search_security_findings returns PLUS: 1. Check Metadata (information about the check script that generated the finding): - title: Human-readable phrase used to summarize the check - description: Detailed explanation of what the check validates and why it is important - risk: What could happen if this check fails - remediation: Complete remediation guidance including step-by-step instructions and code snippets with best practices to fix the issue: cli: Command-line commands to fix the issue terraform: Terraform code snippets with best practices nativeiac: Provider native Infrastructure as Code code snippets with best practices to fix the issue other: Other remediation code snippets with best practices, usually used for web interfaces or other tools * recommendation: Text description with general best recommended practices to avoid the issue - provider: Cloud provider (aws/azure/gcp/etc) - service: Service name (s3/ec2/keyvault/etc) - resource_type: Resource type being evaluated - categories: Security categories this check belongs to - additional_urls: List of additional URLs related to the check 2. Temporal Metadata: - inserted_at: When this finding was first inserted into database - updated_at: When this finding was last updated - first_seen_at: When this finding was first detected across all scans 3. Relationships: - scan_id: UUID of the scan that generated this finding - resource_ids: List of UUIDs for cloud resources associated with this finding Workflow: 1. Use prowler_search_security_findings to browse and filter findings 2. Use this tool with the finding 'id' to get remediation guidance and complete context

prowler_get_finding_group_details

Claude
Get complete details for one finding group by exact check ID. Uses filter[check_id] exact matching against latest data by default, or historical data when dates are provided. Fully muted groups are included by default so accepted risk does not look like a missing group.

prowler_get_findings_overview

Claude
Get aggregate statistics and trends about security findings as a markdown report. This tool provides a HIGH-LEVEL OVERVIEW without retrieving individual findings. Use this when you need to understand the overall security posture, trends, or remediation progress across all findings. The markdown report includes: 1. Summary Statistics: - Total number of findings - Failed checks (security issues) with percentage - Passed checks (no issues) with percentage - Muted findings (user-suppressed) with percentage 2. Delta Analysis (Change Tracking): - New findings: never seen before in previous scans Broken down by: new failures, new passes, new muted - Changed findings: status changed since last scan Broken down by: changed to fail, changed to pass, changed to muted - Unchanged findings: same status as previous scan This helps answer questions like: - "What's my overall security posture?" - "How many critical security issues do I have?" - "Are we improving or getting worse over time?" - "How many new security issues appeared since last scan?"

prowler_get_integration

Claude
Retrieve an integration with its complete, integration-type specific configuration. IMPORTANT: Credentials are never returned by Prowler, only the configuration. This tool provides ALL information that prowler_list_integrations returns PLUS the 'configuration' object, whose contents depend on the integration type: - amazon_s3: 'bucket_name' and 'output_directory' - aws_security_hub: 'send_only_fails', 'archive_previous_findings' and 'enabled_regions' (the AWS regions Security Hub is enabled in, discovered by the connection check) - jira: 'domain', 'projects' (a mapping of project key to project name) and 'issue_types' (a mapping of project key to its available issue types). Both are discovered by the connection check, so an empty 'projects' means the connection has not been checked yet Workflow: 1. Use prowler_list_integrations to find the integration 'id' 2. Use this tool to read its configuration 3. For Jira, read 'projects' here before calling prowler_get_jira_issue_types

prowler_get_jira_issue_types

Claude
List the issue types available in a Jira project. Prowler fetches them live from Jira and stores them in the integration configuration, so the answer is always current. IMPORTANT: The project key must already be present in the 'projects' mapping of the integration configuration. That mapping is discovered by the connection check, so run prowler_test_integration_connection first if it is empty. NOTE: Issue types that require custom fields Prowler does not fill, such as Epic, will be listed here but fail when actually creating the work item. Prefer Task, Bug or Story. Workflow: 1. Use prowler_get_integration to read the 'projects' mapping and pick a project key 2. Use this tool to get the valid issue types for that project 3. Use prowler_send_findings_to_jira with the chosen project key and issue type

prowler_get_mute_rule

Claude
Retrieve comprehensive details about a specific mute rule by its ID. IMPORTANT: This tool returns COMPLETE mute rule details including the full list of finding UIDs. Use this after finding a rule via prowler_list_mute_rules. This tool provides ALL information that prowler_list_mute_rules returns PLUS: - finding_uids: Complete list of finding UIDs that are muted by this rule - user_creator_id: UUID of the user who created the rule (audit trail) Workflow: 1. Use prowler_list_mute_rules to find rules by name or filter criteria 2. Use this tool with the rule 'id' to get complete details 3. Examine finding_uids list to understand which findings are muted 4. Use prowler_update_mute_rule or prowler_delete_mute_rule to modify if needed

prowler_get_mutelist

Claude
Retrieve the current mutelist configuration for the tenant. IMPORTANT: Only one mutelist can exist per tenant. Fails with a message saying so if no mutelist exists. For detailed information about mutelist structure and configuration, search Prowler documentation using prowler_docs_search tool available in this MCP Server. The mutelist includes: - Core identification: id (UUID for processor operations) - Configuration: Nested structure with Accounts → Checks → Regions/Resources/Tags/Exceptions patterns - Temporal data: inserted_at, updated_at timestamps Workflow: 1. Use this tool to check if a mutelist is configured 2. Examine current muting patterns before making updates 3. Use prowler_set_mutelist to create or update the configuration

prowler_get_resource

Claude
Retrieve comprehensive details about a specific resource by its ID. IMPORTANT: This tool provides COMPLETE resource details with all available information. Use this after finding a specific resource via prowler_list_resources. This tool provides ALL information that prowler_list_resources returns PLUS: 1. Configuration Details: - metadata: Provider-specific configuration (tags, policies, encryption settings, network rules) - partition: Provider-specific partition/region grouping (e.g., aws, aws-cn, aws-eusc, aws-us-gov for AWS) 2. Temporal Tracking: - inserted_at: When Prowler first discovered this resource - updated_at: When resource configuration last changed 3. Security Relationships: - finding_ids: Prowler's internal UUIDs (v4) of all security findings associated with this resource - Use prowler_get_finding_details on these IDs to get remediation guidance Useful Workflow: 1. Use prowler_list_resources to browse and filter across many resources 2. Use this tool to drill down into specific resources of interest 3. Use prowler_get_finding_details to get details about the security issues for specific resources

prowler_get_resource_events

Claude
Get the timeline of cloud API actions performed on a specific resource. IMPORTANT: Currently only available for AWS resources. Uses CloudTrail to retrieve the modification history of a resource, showing who did what and when. Each event includes: - What happened: event_name (e.g., PutBucketPolicy), event_source (e.g., s3.amazonaws.com) - Who did it: actor, actor_type, actor_uid - From where: source_ip_address, user_agent - What changed: request_data, response_data (full API payloads) - Errors: error_code, error_message (if the action failed) Use cases: - Investigating security incidents (who modified this resource?) - Change tracking and audit trails - Understanding resource configuration drift - Identifying unauthorized or unexpected modifications Workflows: 1. Resource browsing: prowler_list_resources → find resource → this tool for event history 2. Incident investigation: prowler_get_finding_details → get resource ID from finding → this tool to identify who caused the issue, what they changed, and when

prowler_get_resources_overview

Claude
Generate a markdown overview of your resources with statistics and insights. IMPORTANT: This tool provides HIGH-LEVEL STATISTICS without returning individual resources. Use this when you need a summary view before drilling into details. The report includes: - Total number of resources - Available services across your providers - Regions where resources are deployed - Resource types present in your providers Output format: Markdown-formatted report ready to present to users or include in documentation. Use cases: - Understanding infrastructure footprint - Identifying resource concentration (which regions, services) - Multi-provider deployment auditing - Resource inventory reporting - Tags planning (by provider, service, region)

prowler_get_role

Claude
Retrieve detailed information about a specific role by its ID. Returns everything prowler_list_roles returns PLUS: - permissions: The management capabilities the role grants (only the enabled ones). Read permission_state for the authoritative summary: 'unlimited' means the role grants every capability, including any this deployment does not list individually - unlimited_visibility: Whether the role can see all providers or only its provider groups - provider_group_ids: Provider groups the role is scoped to (empty list means it is scoped to no provider group) - user_ids: Users the role is assigned to (empty list means it is assigned to no user) - inserted_at / updated_at: Lifecycle timestamps The user_ids and provider_group_ids fields are always present: an empty list means "none", not "unknown". Workflow: 1. Use prowler_list_roles to browse roles and find the target role 'id' 2. Use this tool with that 'id' to inspect exactly what the role grants

prowler_get_scan

Claude
Retrieve comprehensive details about a specific scan by its ID. IMPORTANT: This tool returns COMPLETE scan details. Use this after finding a specific scan via prowler_list_scans. This tool provides ALL information that prowler_list_scans returns PLUS: 1. Execution Details: - progress: Scan completion progress as percentage (0-100%) - duration: Total scan duration in seconds from start to completion - unique_resource_count: Number of unique cloud resources discovered during the scan 2. Temporal Metadata: - inserted_at: When the scan was created in the database - scheduled_at: When the scan was scheduled to run (for scheduled scans) - next_scan_at: When the next scan will run (for recurring daily scans) Useful for: - Monitoring scan progress during execution (via progress field) - Viewing scan results and metrics after completion - Debugging failed scans with detailed state information - Understanding scan scheduling patterns Workflow: 1. Use prowler_list_scans to browse and filter scans 2. Use this tool with the scan 'id' to monitor progress or view detailed results 3. For completed scans, use prowler_search_security_findings filtered by date to analyze findings

prowler_get_user

Claude
Retrieve detailed information about a specific user by their ID. Returns everything prowler_list_users returns PLUS: - date_joined: When the user joined - is_verified: Whether the user confirmed their email address (Prowler Cloud only; omitted elsewhere) - role_ids: UUIDs of the roles assigned to the user - membership_ids: UUIDs of the user's tenant memberships Reading another user's roles/memberships requires MANAGE_ACCOUNT; without it the API hides them and role_ids/membership_ids are omitted rather than reported as empty. Workflow: 1. Use prowler_list_users to browse users and find the target user 'id' 2. Use this tool with that 'id' to inspect the user's roles and account details

prowler_get_user_roles

Claude
List the roles currently assigned to a specific user. Returns the user's roles with the concrete capabilities each one grants, so you can see what the user is allowed to do in the tenant. A user normally holds a single role. Note: this reads the user's record, so it requires MANAGE_USERS (the same permission prowler_get_user needs). Each role's user_ids and provider_group_ids are not resolved here; use prowler_get_role for a role's full assignment and provider-group scope. Workflow: 1. Use prowler_list_users (or prowler_get_current_user) to find the user 'id' 2. Use this tool to see which role they hold and what it grants 3. Use prowler_set_user_role to change it

prowler_hub_get_check_code

Claude
Fetch the Python implementation code of a Prowler security check. 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: { "content": "Python source code of the check implementation" }

prowler_hub_get_check_details

Claude
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

prowler_hub_get_check_fixer

Claude
Fetch the auto-remediation (fixer) code for a Prowler security check. IMPORTANT: Not all checks have fixers. A check with no auto-remediation code fails with a message saying so - this is normal for many checks and not a problem to report or retry. Fixer code provides automated remediation that can fix security issues detected by checks. Use this to understand how to programmatically remediate findings. Returns: { "content": "Python source code of the auto-remediation implementation" }

prowler_hub_get_compliance_details

Claude
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"] } ] }

prowler_hub_get_provider_services

Claude
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: { "provider_id": "aws", "provider_name": "Amazon Web Services", "count": N, "services": ["s3", "ec2", "iam", "rds", "lambda", ...] }

prowler_hub_list_checks

Claude
List security Prowler Checks with filtering capabilities. 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: { "count": N, "checks": [ { "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

prowler_hub_list_compliances

Claude
List compliance frameworks supported by Prowler. 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: { "count": N, "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

prowler_hub_list_providers

Claude
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: { "count": N, "providers": [ { "id": "aws", "name": "Amazon Web Services" }, { "id": "azure", "name": "Microsoft Azure" }, ... ] }

prowler_hub_semantic_search_checks

Claude
Search for security checks using free-text search across all metadata. 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: { "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

prowler_hub_semantic_search_compliances

Claude
Search for compliance frameworks using free-text search. 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: { "count": N, "compliances": [ { "id": "cis_4.0_aws", "name": "CIS Amazon Web Services Foundations Benchmark v4.0", "provider": "aws", }, ... ] }

prowler_list_attack_paths_queries

Claude
Discover available Attack Paths queries for a completed scan. IMPORTANT: The scan must be in 'completed' state to list queries. Attack Paths covers AWS providers only, so only an AWS provider has an Attack Paths scan to name here, and every query is an AWS one. Each query includes: - id: Query identifier to use with run_attack_paths_query - name: Human-readable name describing what the query finds - description: Detailed explanation of the security analysis - parameters: List of required parameters (if any) Example queries (AWS): - aws-internet-exposed-ec2-sensitive-s3-access: Find EC2 instances exposed to internet with access to sensitive S3 buckets - aws-iam-privesc-passrole-ec2: Detect privilege escalation via PassRole + EC2 - aws-ec2-instances-internet-exposed: Find internet-exposed EC2 instances Workflow: 1. Use prowler_list_attack_paths_scans to find a completed scan 2. Use this tool to discover available queries 3. Use prowler_run_attack_paths_query with query_id and any required parameters

prowler_list_attack_paths_scans

Claude
List Attack Paths scans with filtering capabilities. Default behavior: - Returns COMPLETED scans (ready for attack paths analysis) - Returns 50 scans per page - Shows the latest scan per provider Each scan includes: - Core identification: id (UUID for get/query operations) - Execution context: state, progress - Provider info: provider_id, provider_alias, provider_type, provider_uid Workflow: 1. Use this tool to find completed attack paths scans 2. Use prowler_list_attack_paths_queries to see available queries for a scan 3. Use prowler_run_attack_paths_query to execute analysis

prowler_list_finding_group_resources

Claude
List resources affected by a finding group. Without dates this uses /finding-groups/latest/{check_id}/resources. With date_from or date_to, this uses /finding-groups/{check_id}/resources with a maximum 2-day date window. Default behavior returns FAIL, unmuted resources so the result is actionable. Set include_muted=True to include accepted/suppressed resources too. Each row includes nested resource and provider data plus finding_id. Use prowler_get_finding_details(finding_id) to retrieve complete remediation guidance for a specific resource finding.

prowler_list_finding_groups

Claude
List finding groups aggregated by check ID. Default behavior returns the latest non-muted FAIL groups for fast triage. Without dates this uses /finding-groups/latest. With date_from or date_to, this uses /finding-groups with a maximum 2-day date window. Use this tool to find noisy or high-impact checks, then call prowler_get_finding_group_details for complete counters or prowler_list_finding_group_resources to drill into affected resources.

prowler_list_integrations

Claude
List the integrations configured in Prowler, with their connection state. Integrations are the destinations Prowler sends its results to. They are configured per tenant and require the 'manage_integrations' permission. IMPORTANT: This tool returns LIGHTWEIGHT integrations without the integration-type specific configuration. Use prowler_get_integration to get the full configuration, such as the S3 bucket name or the available Jira projects. Default behavior: - Returns every integration type - Returns 50 integrations per page. Tenants normally have a handful of them, so the first page usually contains all of them Each integration includes: - Core identification: id (UUID for prowler_get_integration), integration_type - State: enabled, connected (true, false, or null when never checked), connection_last_checked_at - Scope: provider_ids, the providers the integration is attached to. Empty means it applies to the whole tenant, which is always the case for Jira - Temporal data: inserted_at, updated_at timestamps NOTE: The API does not support filtering by 'enabled' or 'connected'. Read those fields from the returned results instead. Workflow: 1. Use this tool to see which integrations exist and whether they are working 2. Use prowler_get_integration with the 'id' to get the full configuration 3. Use prowler_test_integration_connection to re-check a broken integration 4. Use prowler_update_integration to fix credentials or settings

prowler_list_mute_rules

Claude
Search and filter mute rules with pagination support. IMPORTANT: This tool returns LIGHTWEIGHT mute rules without the full list of finding UIDs. Use prowler_get_mute_rule to get complete details including all finding UIDs and creator information. Default behavior: - Returns all mute rules (both enabled and disabled) - Returns 50 rules per page - Includes basic rule information without full finding UID lists Each mute rule includes: - Core identification: id (UUID for prowler_get_mute_rule), name - Contextual information: reason, enabled status - State tracking: finding_count (number of findings currently muted) - Temporal data: inserted_at, updated_at timestamps Workflow: 1. Use this tool to search and filter mute rules by name, enabled status, or keywords 2. Use prowler_get_mute_rule with the mute rule 'id' to get complete details including all finding UIDs 3. Use prowler_update_mute_rule or prowler_delete_mute_rule to modify rules

prowler_list_resources

Claude
List and filter all resources scanned by Prowler. IMPORTANT: This tool returns LIGHTWEIGHT resource information. Use this for fast searching and filtering across many resources. For complete configuration details, metadata, and finding relationships, use prowler_get_resource on specific resources of interest. This is the primary tool for browsing resources with rich filtering capabilities. Returns current state by default (latest scan per provider). Specify dates to query historical data (2-day maximum window). Default behavior: - Returns latest resources from most recent scans (no date parameters needed) - Returns 50 results per page - Sorted by service, region, and name for logical grouping Date filtering: - Without dates: queries resources from the most recent completed scan per provider (most efficient) - With dates: queries historical resource state (2-day maximum range between date_from and date_to) Each resource includes: - Core identification: id (UUID for prowler_get_resource), uid, name - Location context: region, service, type - Security context: failed_findings_count (number of active security issues) - Tags: tags associated with the resource Useful Workflow: 1. Use this tool to search and filter resources by provider, region, service, tags, etc. 2. Use prowler_get_resource with the resource 'id' to get complete configuration and metadata 3. Use prowler_search_security_findings to find security issues for specific resources 4. Use prowler_get_finding_details to get details about the security issues for specific resources

prowler_list_roles

Claude
List the RBAC roles defined in the authenticated tenant. Use this to discover which roles exist and their permission scope before assigning one to a user. Returns LIGHTWEIGHT role information. Each role includes: - id: Prowler internal UUID (v4), used with prowler_get_role and the assignment tools - name: Human-readable role name - permission_state: Summary of what the role grants ('unlimited', 'limited' or 'none') For the concrete capabilities a role grants and the users/provider groups it relates to, use prowler_get_role.

prowler_list_scans

Claude
List and filter security scans across all providers with rich filtering capabilities. IMPORTANT: This tool returns LIGHTWEIGHT scan information. Use this for fast searching and filtering across many scans. For complete scan details including progress, duration, and resource counts, use prowler_get_scan on specific scans of interest. Default behavior: - Returns all scans - Returns 50 scans per page - Includes all scan states (available, scheduled, executing, completed, failed, cancelled) Each scan includes: - Core identification: id (UUID for prowler_get_scan), name - Execution context: state, trigger (manual/scheduled), is_partial (partial or full scan) - Temporal data: started_at, completed_at - Provider relationship: provider_id Workflow: 1. Use this tool to search and filter scans by provider, state, or date range 2. Use prowler_get_scan with the scan 'id' to get progress, duration, and resource counts 3. Use prowler_search_security_findings filtered by scan dates to analyze scan results

prowler_list_users

Claude
List the users that belong to the authenticated tenant. Use this to see who has access to the tenant and to look up their email addresses. Returns LIGHTWEIGHT user information optimized for browsing. Each user includes: - id: Prowler internal UUID (v4), used with prowler_get_user - name: Display name - email: Email address - company_name: Company the user belongs to, when set To find out which user the current credentials authenticate as, use prowler_get_current_user. For a single user's roles, membership links and join date, use prowler_get_user.

prowler_run_attack_paths_query

Claude
Execute an Attack Paths query and analyze the results. IMPORTANT: This is the PRIMARY tool for attack paths analysis. It executes a Cypher query against the Neo4j graph database and returns the attack path graph with security findings. Prerequisites: - Scan must be in 'completed' state - query_id must be valid for the scan's provider type - All required parameters must be provided Returns: - nodes: Cloud resources, findings, and virtual nodes in the attack path - relationships: Connections between nodes (CAN_ACCESS, STS_ASSUMEROLE_ALLOW, etc.) Node types you may see: - EC2Instance, S3Bucket, RDSInstance, LoadBalancer, etc. (cloud resources) - ProwlerFinding (security issues with severity and status) - Internet (virtual node representing external access) - PrivilegeEscalation (virtual node for escalation outcomes) Relationship types: - CAN_ACCESS: Network access path (often from Internet) - STS_ASSUMEROLE_ALLOW: IAM role assumption - MEMBER_OF_EC2_SECURITY_GROUP: Security group membership - And many more cloud-specific relationships Workflow: 1. Ensure scan is completed 2. List available queries (use prowler_list_attack_paths_queries) 3. Execute this tool with appropriate parameters 4. Analyze the returned graph for security insights

prowler_search_providers

Claude
Search and view configured providers to be scanned with Prowler. This tool returns a unified view of all providers configured in Prowler. For getting more details about what types of providers are available to be scanned with Prowler or what are the UIDs are accepted for each provider type, please refer to Prowler Hub/Prowler Documentation that you can also find in form of tools in this MCP Server. Each provider includes: - Provider identification: Prowler Internal ID, External Provider UID, Provider Alias - Provider context: Provider Type - Connection status: Connected (true), Failed (false), Not Tested (null)

prowler_search_security_findings

Claude
Search and filter security findings across all cloud providers with rich filtering capabilities. IMPORTANT: This tool returns LIGHTWEIGHT findings. Use this for fast searching and filtering across many findings. For complete details use prowler_get_finding_details on specific findings. Default behavior: - Returns latest findings from most recent scans (no date parameters needed) - Filters to FAIL status only (security issues found) - Returns 50 results per page Date filtering: - Without dates: queries findings from the most recent completed scan across all providers (most efficient) - With dates: queries historical findings (2-day maximum range between date_from and date_to) Each finding includes: - Core identification: id (UUID for get_finding_details), uid, check_id - Security context: status (FAIL/PASS/MANUAL), severity (critical/high/medium/low/informational) - State tracking: delta (new/changed/unchanged), muted (boolean), muted_reason - Extended details: status_extended with additional context Workflow: 1. Use this tool to search and filter findings by severity, status, provider, service, region, etc. 2. Use prowler_get_finding_details with the finding 'id' to get complete information about the finding

prowler_send_findings_to_jira

Claude
Create Jira work items from Prowler findings. Each work item carries the finding's check title, severity, status, provider, region, resource, risk description and remediation steps. Selecting the findings, exactly one of the two is required: - finding_ids: the exact findings to send, whatever their status or scan - check_ids: PROWLER CLOUD ONLY. Prowler resolves the failing findings of those checks itself, from the latest completed scan of every provider. Deployments other than Prowler Cloud reject this filter with a client error Dispatch modes, PROWLER CLOUD ONLY: - 'individual' (default): one work item per finding, and the only mode other deployments support. Combined with 'check_ids' it opens one work item per failing resource of those checks, which can be hundreds of them - 'grouped': one work item per check, listing up to 50 affected resources and linking back to the finding group in Prowler Cloud. Only failed, unmuted findings of the latest completed scan of every provider are grouped, so findings outside that set are left out without being reported WARNING: deployments other than Prowler Cloud ignore 'dispatch_mode' instead of rejecting it, and create one work item per finding. WARNING: This creates real work items in Jira. Prowler cannot delete or update them afterwards, they have to be handled in Jira. Only call this again for the same findings when the previous response had safe_to_retry=true, otherwise it creates duplicates. WARNING: Avoid issue types that require custom fields Prowler does not fill, such as Epic. Creation fails for those. Task, Bug and Story normally work. Default behavior: - One work item per finding, created sequentially, so large batches take a while. A grouped dispatch creates one per check instead, so it is a single work item for a check failing on hundreds of resources - The dispatch runs as a background task and this tool waits up to 5 minutes for it. If it is still running by then, the response has status='in_progress', an 'error' explaining it, and the 'task_id' The result includes: - status: 'completed' when Prowler finished the dispatch, 'in_progress' when the task is still running, 'failed' when the dispatch was rejected before it started, 'unknown' when the task stopped without reporting a result - safe_to_retry: whether the dispatch can be sent again. It is only true when no work item was created, which is the case when the dispatch was rejected before it started. NEVER call this tool again for the same findings when it is false, the work items already created would be duplicated. Report the outcome to the user and let them check Jira instead - created_count: number of work items created in Jira, absent unless status='completed'. In 'grouped' mode this counts work items, one per check, not findings - failed_count: number of findings that could not be sent, absent unless status='completed'. In 'grouped' mode it counts the entries of failed_groups, normally one per check rather than one per finding - failed_groups: in 'grouped' mode only, the failures behind failed_count, each with the reason and the 'check_id' whose work item could not be created, or a 'finding_id' instead when Prowler could not read that finding to tell which check it belongs to Workflow: 1. Use prowler_search_security_findings to select the findings to escalate, or prowler_list_finding_groups to pick the checks to escalate as a whole 2. Use prowler_get_integration to read the 'projects' mapping and pick a project key 3. Use prowler_get_jira_issue_types to pick a valid issue type 4. Use this tool with the finding IDs, or with the check IDs and dispatch_mode='grouped' to open a single work item per check

prowler_set_mutelist

Claude
Create or update the mutelist configuration for pattern-based bulk muting. IMPORTANT: Automatically creates a new mutelist or updates the existing one (only one mutelist per tenant). The configuration completely replaces any existing mutelist (not merged). For detailed information about mutelist structure and configuration, search Prowler documentation using prowler_docs_search tool available in this MCP Server. Default behavior: - Creates new mutelist if none exists - Updates existing mutelist with complete replacement - Applies to findings from future scans The mutelist supports: - Account patterns: Specific account IDs or "*" for all - Check-based muting: Per-check ID configuration - Scope filtering: Regions, Resources, Tags - Exceptions: Accounts, Regions, Resources to exclude from muting Workflow: 1. Use prowler_get_mutelist to check existing configuration 2. Build configuration object following Prowler mutelist format 3. Use this tool to create or update the mutelist 4. Verify with prowler_get_mutelist

prowler_set_user_role

Claude
Set the role a user holds, replacing the role they had before. A user holds exactly one role in Prowler: their permissions are resolved from a single role, so granting a new one REPLACES the previous one instead of adding to it. To change what a user can do, set the role that grants the capabilities they should have. This tool is idempotent: if the user already holds only this role, it makes no change and reports changed: false. It always returns the user's up-to-date role after the operation. Note: this operation requires both MANAGE_ACCOUNT (to change role assignments) and MANAGE_USERS (to read the user's current role). The API rejects the change when it would leave the tenant without a user holding MANAGE_ACCOUNT; such rejections are surfaced as errors. Workflow: 1. Use prowler_list_roles to find the role 'id' to grant 2. Use prowler_list_users to find the target user 'id' 3. Use this tool to set the user's role

prowler_test_integration_connection

Claude
Check that Prowler can reach an integration with its stored credentials. This also refreshes the parts of the configuration that Prowler discovers from the remote system, so it is the way to repair a stale configuration: - jira: repopulates 'projects' and 'issue_types' - aws_security_hub: repopulates 'enabled_regions' IMPORTANT: A disabled integration is never checked. It comes back as 'failed' with the error 'Integration is not enabled'. Enable it first with prowler_update_integration. The check runs as a background task and this tool waits for it, so it can take a few seconds to return. Workflow: 1. Use prowler_list_integrations to spot integrations with connected=false 2. Use this tool to re-check one after fixing its permissions on the remote side 3. If it still fails, read 'error' and fix the credentials with prowler_update_integration

prowler_trigger_scan

Claude
Trigger a manual security scan for a provider. IMPORTANT: This tool returns immediately once the scan is created. The scan will continue running in the background. Use prowler_get_scan with the returned scan ID to monitor progress and check when it completes. Example Useful Workflow: 1. Use prowler_search_providers to find the provider_id you want to scan 2. Use this tool to trigger the scan 3. Use prowler_get_scan with the returned scan 'id' to monitor progress 4. Once completed, use prowler_search_security_findings to analyze results Partial scan (pass resource_uids): re-checks just those resources, e.g. to confirm a remediation without waiting for a full scan. Only the checks the provider's latest completed scan reported for them are re-run; once it completes, their latest findings (what prowler_search_security_findings returns by default) reflect the new results, and every other resource keeps its findings from the latest full scan. Prowler refuses it, with the reason, when the provider has no completed scan yet (run a full scan first), a uid matches no resource of the provider, the latest completed scan has no findings for those resources, or the provider already has a scan running or queued (wait for it to finish, then retry).

prowler_update_integration

Claude
Update an integration's credentials, configuration, providers or enabled state. The integration type cannot be changed. To switch types, delete the integration and create a new one. Default behavior: - Only the parameters provided are changed, everything else is preserved - 'configuration' is merged with the current one, so partial updates are safe - When 'credentials', 'configuration' or the attached providers change, the connection is re-checked and the result is part of the response. Toggling only 'enabled' does not re-check it Constraints: - Jira integrations reject 'configuration' and 'provider_ids'. Sending a configuration would wipe the discovered 'projects' and 'issue_types', so this tool refuses it - Jira 'credentials' are replaced as a whole, so 'domain', 'user_mail' and 'api_token' are all required. An empty or partial object is refused because it would destroy the stored credentials - Security Hub integrations must keep exactly one AWS provider, so 'provider_ids' has to contain a single ID. Use prowler_delete_integration to stop sending findings - The 'enabled_regions' of a Security Hub integration are server-owned and cannot be set here, they are refreshed by the connection check Workflow: 1. Use prowler_get_integration to read the current configuration 2. Use this tool with only the fields to change 3. Read 'connected' in the response to confirm the integration still works

prowler_update_mute_rule

Claude
Update a mute rule's name, reason, or enabled status. IMPORTANT: Cannot change which findings are muted (finding_uids are immutable). Disabling a rule does NOT un-mute findings - they remain muted permanently. Default behavior: - Only specified fields are updated - Unspecified fields remain unchanged - If no parameters provided, returns current rule state Updatable fields: - name: Change rule name for better organization - reason: Update documentation/justification - enabled: Toggle rule active status (doesn't affect already-muted findings) Workflow: 1. Use prowler_get_mute_rule to see current rule state 2. Use this tool to update name, reason, or enabled status 3. Verify changes with prowler_get_mute_rule

prowler_update_scan

Claude
Update a scan's name for better organization and tracking. IMPORTANT: Only the scan name can be updated. Other scan attributes (state, progress, duration, etc.) are read-only and managed by the system. Example Useful Workflow: 1. Use prowler_list_scans to find the scan you want to rename 2. Use this tool with the scan 'id' and new name

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/prowler-cloud-for-claude-code"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/prowler-cloud-for-claude-code)