Skip to main content
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 clients, allowing interaction with Prowler’s security capabilities through natural language.
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 or join our Slack community to discuss and share your thoughts.

Quickest Way to Connect: Cloud MCP Server

The fastest way to get started is the Cloud MCP Server at https://mcp.prowler.com/mcp — no installation, always up to date, and maintained by Prowler. Just point your MCP client at the URL and authenticate with a Prowler API key as a Bearer token:

Connect Your MCP Client to the Cloud MCP Server

Step-by-step setup for Claude Code, Codex, Cursor, VS Code, and other agents.
Prefer to run it yourself? The Local MCP Server runs on your own machine or infrastructure. The Cloud MCP Server additionally provides the prowler_cloud_* tools for Prowler Cloud-specific features: Alerts, Findings Triage, Scan Scheduling, and Scan Configurations. See Cloud vs Local MCP Server.

What is the Model Context Protocol?

The Model Context Protocol (MCP) is an open standard developed by Anthropic that enables AI assistants to securely connect to external data sources and tools. It functions as a universal adapter enabling AI assistants to interact with various services through a standardized interface.

Key Capabilities

The Prowler MCP Server provides four integration points:

1. Prowler Cloud, Private Cloud & Local Server

Full access to your Prowler deployment — Prowler Cloud, Prowler Private Cloud, or Prowler Local Server — 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, track their progress, and schedule a daily scan
  • Resource Inventory: Search and view detailed information about your audited resources
  • Muting Management: Create and manage muting lists/rules to suppress non-relevant findings
  • Attack Paths Analysis: Analyze privilege escalation chains and security misconfigurations through graph-based analysis of cloud resource relationships
  • Integrations Management: Set up and troubleshoot where Prowler sends its results (Amazon S3, AWS Security Hub, Jira), and turn findings into Jira work items
  • User & Role Management: List the users in your tenant, identify the authenticated user, browse RBAC roles, and set the role a user holds

2. Prowler Cloud Management

Prowler Cloud-only tools for configuration and workflows that a Prowler Local Server does not provide. These are exposed only by the Cloud MCP Server:
  • Scan Configurations: Create reusable check and compliance selections and attach them to providers.
  • Findings Triage: Record review statuses and notes for individual findings, without suppressing them.
  • Scan Scheduling: Configure daily, interval, weekly, or monthly recurring scans, one provider at a time or in bulk.
  • Alerts: Build and dry-run alert rule conditions, manage email recipients, and review fired alerts.

3. Prowler Hub

Access to Prowler’s comprehensive security knowledge base:
  • Security Checks Catalog: Browse and search over 2,000 security checks across multiple cloud 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 each cloud provider.

4. 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.

MCP Server Architecture

The following diagram illustrates the Prowler MCP Server architecture and its integration points. MCP clients connect to either the Cloud MCP Server (recommended) or a Local MCP Server. Both reach the same Prowler backends and share the prowler_*, prowler_hub_*, and prowler_docs_* tools; the Cloud MCP Server additionally exposes the Cloud-only prowler_cloud_* tools: The architecture shows how AI assistants connect through the MCP protocol to access Prowler’s four namespaced components:
  • Prowler Cloud, Prowler Private Cloud, or Prowler Local Server for security operations
  • Prowler Cloud management for Cloud-only configuration and workflows
  • Prowler Hub for security knowledge
  • Prowler Documentation for guidance and reference.

Use Cases

The Prowler MCP Server enables powerful workflows through AI assistants: 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 flag the ones whose mute reason is too weak for their severity”
  • “Run an attack paths query to find EC2 instances exposed to the Internet with access to sensitive S3 buckets”
  • “Send my failed CIS findings for this provider to Jira as work items”
Prowler Cloud Management (Cloud MCP Server only)
  • “Preview an alert rule for critical AWS findings and create it for my confirmed recipients”
  • “Show the triage notes for this finding and mark it as under review”
  • “Apply a weekly Monday 06:00 scan schedule to every AWS provider”
  • “Create a scan configuration that runs only CIS checks and attach it to my production providers”
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?”
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?”

Example: Creating a custom dashboard with Prowler extracted data

In the next example you can see how to create a dashboard using Prowler MCP Server and Claude Desktop. Used Prompt:
Video:

Cloud vs Local MCP Server

There are two ways to run the Prowler MCP Server. For almost everyone, the Cloud MCP Server is the right choice — it needs no installation and is maintained by Prowler. The Local MCP Server exists for users who need to run it on their own machine or infrastructure. Prowler’s managed MCP server at https://mcp.prowler.com/mcp. No installation, always up to date, and it includes the prowler_cloud_* tools for Prowler Cloud-specific features: Alerts, Findings Triage, Scan Scheduling, and Scan Configurations. This is the path we recommend for nearly all users — go straight to the Configuration guide.

💻 Local MCP Server

Run the server yourself when you need full control over the deployment. It connects to Prowler Cloud, Prowler Private Cloud, or Prowler Local Server and can run in two modes:
  • STDIO mode — the server runs as a subprocess of your MCP client. Authentication via environment variables.
  • Self-hosted HTTP mode — deploy your own remote HTTP server. Authentication via API key or JWT token.
Both require Python 3.12+ or Docker, plus network access to https://hub.prowler.com (Prowler Hub), https://docs.prowler.com (Prowler Documentation), and the Prowler API or Prowler Local Server API (Prowler features). See the Installation guide to get started.
No Authentication Required: Prowler Hub and Prowler Documentation features work without authentication on both the Cloud and Local MCP Server. A Prowler API key is only required to access Prowler features (Prowler Cloud, Prowler Private Cloud, or Prowler Local Server).

Next Steps

Configuration

Connect your MCP client to the Cloud MCP Server

Tools Reference

Explore all available tools and capabilities

Local Installation

Run the Local MCP Server yourself using Docker, source, or uvx

Related topics

Overview