prowler-mcp

Creates MCP tools for Prowler MCP Server. Covers BaseTool pattern, model design, and API client usage. Use when working on mcp_server/ directory.

⭐12.5kstars🔀1.9kforks📁View on GitHub🕐Updated Jan 10, 2026⬇️2downloads

When & Why to Use This Skill

This Claude skill streamlines the development of MCP (Model Context Protocol) tools specifically for the Prowler MCP Server. It automates the implementation of the BaseTool pattern, enforces strict architectural rules for data modeling using MinimalSerializerMixin, and ensures standardized API client usage, significantly reducing boilerplate and development errors for security and cloud management integrations.

Use Cases

  • Rapidly scaffolding new cloud management tools within the prowler_app directory by following the required BaseTool inheritance and auto-registration patterns.
  • Designing and implementing standardized data models that transform raw API responses into simplified or detailed formats for consistent LLM consumption.
  • Performing automated QA checks on MCP tool implementations to ensure compliance with Prowler's specific error handling, parameter description, and security protocols.
nameprowler-mcp
description>
TriggerWhen working in mcp_server/ on tools (BaseTool), models (MinimalSerializerMixin/from_api_response), or API client patterns.
licenseApache-2.0
authorprowler-cloud
version"1.0"
scope[root, mcp_server]
auto_invoke"Working on MCP server tools"
allowed-toolsRead, Edit, Write, Glob, Grep, Bash, WebFetch, WebSearch, Task

Overview

The Prowler MCP Server uses three sub-servers with prefixed namespacing:

Sub-Server Prefix Auth Purpose
Prowler App prowler_app_* Required Cloud management tools
Prowler Hub prowler_hub_* No Security checks catalog
Prowler Docs prowler_docs_* No Documentation search

For complete architecture, patterns, and examples, see docs/developer-guide/mcp-server.mdx.


Critical Rules (Prowler App Only)

Tool Implementation

  • ALWAYS: Extend BaseTool (auto-registered via tool_loader.py, only public methods from the class are exposed as a tool)
  • NEVER: Manually register BaseTool subclasses
  • NEVER: Import tools directly in server.py

Models

  • ALWAYS: Use MinimalSerializerMixin for responses
  • ALWAYS: Implement from_api_response() factory method
  • ALWAYS: Use two-tier models (Simplified for lists, Detailed for single items)
  • NEVER: Return raw API responses

API Client

  • ALWAYS: Use self.api_client singleton
  • ALWAYS: Use build_filter_params() for query parameters
  • NEVER: Create new httpx clients

Hub/Docs Tools

Use @mcp.tool() decorator directly—no BaseTool or models required.


Quick Reference: New Prowler App Tool

  1. Create tool class in prowler_app/tools/ extending BaseTool
  2. Create models in prowler_app/models/ using MinimalSerializerMixin
  3. Tools auto-register via tool_loader.py

QA Checklist (Prowler App)

  • Tool docstrings describe LLM-relevant behavior
  • Models use MinimalSerializerMixin
  • API responses transformed to simplified models
  • Error handling returns {"error": str, "status": "failed"}
  • Parameters use Field() with descriptions
  • No hardcoded secrets

Resources