PDF Mcp

PDF MCP is a robust Model Context Protocol (MCP) server that equips AI assistants and agentic AI tools with advanced PDF capabilities, including extracting document information, reading pages or entire documents, full-text and semantic search, table and image extraction, and intelligent caching. Built in Python and using PyMuPDF with SQLite-based persistent caching, PDF MCP is production-ready and supports multi-client integration (Claude, Copilot, Cursor, VS Code, and more). Designed for AI developers, knowledge workers, and enterprise teams leveraging AI for document analysis, it streamlines and enhances PDF-related workflows for MCP-compatible environments. No cloud processing is required—semantic search runs locally.