MCP Local RAG

Privacy-first local RAG server for developers that runs entirely on-device with zero cloud dependencies. Combines semantic search via embeddings with keyword boost for exact technical terms like function names, error codes, and class names. Uses smart semantic chunking that splits documents by meaning rather than character count. Supports PDF, DOCX, and TXT files with optional vision-language model for PDF visual parsing. Zero-friction setup via npx with no Docker or Python required. Works fully offline after initial model download. 340 GitHub stars.

MCP unverified

Integration

Transport	`stdio`
Auth	`none`
Endpoint	MCP Local RAG
Install	`npx -y mcp-local-rag`

Use Cases

01	Search local documents with semantic understanding and keyword boosting for technical terms using a fully private on-device RAG server with zero cloud dependencies
02	Index code documentation, technical specs, and reference materials locally for AI-assisted development in Claude Code or Cursor without sending data to external services
03	Run privacy-first document retrieval with smart semantic chunking and optional vision-language PDF parsing in air-gapped or compliance-sensitive development environments