rag-mcp is a local hybrid-search MCP server for AI coding agents and technical document workflows. It combines Tantivy BM25 lexical search, LanceDB vector retrieval, reciprocal rank fusion, and cross-encoder reranking to return evidence with source paths and line ranges.
rag-mcp sits in PulseGate's RAG, search & retrieval category. It focuses on finding relevant code and technical documentation without manually inspecting files or sending repositories to cloud services. rag-mcp is an open-source project aimed at developers building or using AI coding agents. rag-mcp is open source under the Open Source license. It ships for the web and the command line, and it can be self-hosted.
Behind rag-mcp is Masih Moafi. Among its 9 catalogued features are BM25 search, vector retrieval, and result fusion. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do