mcp-mcp
Verified Safeby wojtyniak
Overview
A Meta-MCP server to discover, suggest, and potentially provision other Model Context Protocol (MCP) servers for AI assistants.
Installation
uvx mcp-mcpEnvironment Variables
- MCPMCP_DEBUG
- XDG_CACHE_HOME
Security Notes
The server includes explicit `OriginValidationMiddleware` to prevent DNS rebinding attacks and restrict access to `localhost`/`127.0.0.1`. All external data fetching uses `httpx` with timeouts and is from trusted GitHub raw content sources. The system does not use `eval` or similar dynamic code execution on untrusted input. No API keys are required for core functionality, reducing the risk of hardcoded secrets. Logging is correctly redirected to `stderr` to avoid interfering with MCP client communication.
Similar Servers
mcp-server
Provides a Model Context Protocol (MCP) server for AI agents to search and retrieve curated documentation for the Strands Agents framework, facilitating AI coding assistance.
toolsdk-mcp-registry
A unified registry and API gateway for discovering, managing, and executing Model Context Protocol (MCP) servers, supporting local and secure sandbox execution with OAuth 2.1 integration.
tmcp
Build Model Context Protocol (MCP) servers for AI agents, providing schema-agnostic tools, resources, and prompts, with optional OAuth 2.1 authentication and distributed session management.
mcp-servers
Provides a curated collection of Model Context Protocol (MCP) server configurations to enable AI agents to interact with various developer tools and services.