Mcp Local Rag

Mcp Local Rag is a privacy-first, fully local semantic search and retrieval-augmented generation (RAG) server designed for developers and technical teams. It enables vector-based and keyword-boosted search across local documentation (PDF, DOCX, TXT, Markdown, and cleaned HTML) with smart semantic chunking, grouping results by relevance, and functioning entirely offline after initial model download. It can be used as a Model Context Protocol (MCP) server or CLI tool, supporting workflows for AI coding assistants like Cursor, Codex, and Claude Code, and offers optional local generation of captions for visual content in PDFs.