rag-mcp
MCP serverScoped hybrid search and grounded answers over local files for coding agents
Runs locally- 1 tool
- Open source
- Knowledge and memory
Scoped hybrid search and grounded answers over local files for coding agents
Runs locally
Local persistent memory for AI agents with search, source citations and encrypted storage
Runs locallySelf-hosted RAG knowledge base with hybrid retrieval, cited answers and an MCP server
Not checked yetStructure-first search over large Markdown libraries, with no embeddings or vector store
Runs locallyLocal full-text search with BM25 ranking and fuzzy matching for Next.js apps
Runs locallyLocal MCP server that reranks and trims RAG context to cut tokens before an LLM call
Runs locallyLocal code search for AI assistants, with AST-aware chunking and no cloud
Runs locallyLocal RAG engine that indexes codebases into a code graph, embeddings and wiki for AI
Not checked yetFull Qdrant API as 58 MCP tools, with plain-text semantic, BM25 and hybrid search
Runs locallyFile cache for coding agents that returns tiny re-reads and diffs
Runs locallyLocal code graph for agents with search, call tracing and change impact analysis
Runs locallyLocal code and document search for AI agents, with an optional paid cloud index
Runs locallyThe closest alternatives to rapidbm25 are rag-mcp, WARM, MiniRAG, MarkIndex and Searchcraft.
Yes. rag-mcp, WARM, MiniRAG have a free or open-source option.