mcp_server
by swapnildagade1213
Overview
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).
Installation
uv run main.pySecurity Notes
Hardcoded sensitive credentials (client_id, client_secret, tenant_id) are present in 'mcp_demo.py', albeit encrypted within the source code. Multiple instances of SSL/TLS certificate verification are explicitly disabled ('verify=False' in requests.get calls and 'NoVerifyHTTPAdapter()' for exchangelib), creating severe man-in-the-middle attack vulnerabilities. The 'decode_jwttoken' tool intentionally disables JWT signature verification, which could lead to misinterpretation or misuse.
Similar Servers
zeromcp
A minimal, pure Python Model Context Protocol (MCP) server for exposing tools, resources, and prompts via HTTP/SSE and Stdio transports.
mcp-server-python-template
This server provides weather forecasting and alert information to LLM applications via the Model Context Protocol (MCP).
mcp-servers
Provides an MCP server for Qdrant vector database integration, enabling AI agents to perform semantic search, store documents, and manage collections with advanced multi-tenant filtering capabilities.
MCP-Council
Automates the conversion of any REST API into a Model Context Protocol (MCP) server, enabling AI assistants to interact with external APIs through a standardized interface.