pymcp
Verified Safeby anirbanbasu
Overview
A modular Model Context Protocol (MCP) server template in Python, providing diverse tools like web search, password generation, and mathematical functions, designed for extensibility and integration with FastMCP clients.
Installation
uv run pymcpSecurity Notes
The server primarily uses standard Python libraries and the FastMCP framework. No direct use of `eval`, `exec`, or other obvious code injection vulnerabilities were found. It uses `secrets` for password generation, which is good practice. The `DDGS` library for web search involves external network requests, which is an inherent, but managed, risk. The `DDGS_PROXY` environment variable allows proxy configuration for these requests, assuming a trusted server configuration. CORS configuration (`ASGI_CORS_ALLOWED_ORIGINS`) defaults to `*`, which is explicitly noted in the code and documentation as insecure for production environments and should be restricted. The implementation of middleware for argument stripping and metadata addition appears robust. Overall, for an example/template server, the security practices are reasonable, with explicit warnings for production deployment considerations.
Similar Servers
mcp_server
Provides a Python server that exposes various external APIs (Microsoft Graph, GitHub, OpenWeatherMap) as tools to be consumed by AI assistants via the Model Context Protocol (MCP).
mcp-server
This server exposes a set of tools and resources, including arithmetic operations, web browser control, data retrieval, and dynamic greetings, accessible via the MCP protocol over HTTP.
mcp-toolbox
Provides a set of utility tools (format conversion, text processing, network checks) exposed via the Model Context Protocol (MCP) for LLMs to consume.
KensMCP
A custom Model Context Protocol (MCP) server that provides a suite of developer utilities for AI assistants to perform real actions.