Easy-to-setup local RAG server with minimal configuration
io.github.shinpr/mcp-local-rag
https://github.com/shinpr/mcp-local-rag
STDIO
No auth required
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Base directory for document storage (defaults to current working directory)
Path to LanceDB database directory (defaults to ./lancedb/)
Directory where Transformers.js models are cached (defaults to ./models/)
Embedding model name (defaults to Xenova/all-MiniLM-L6-v2)
Maximum file size in bytes (defaults to 104857600 / 100MB)
Maximum distance threshold for filtering search results. Results with distance greater than this value will be excluded. Lower values mean stricter filtering (e.g., 0.5 for high relevance only)
Grouping mode for quality filtering. 'similar' returns only the most similar group (stops at first distance jump). 'related' includes related groups (stops at second distance jump). Unset means no grouping filter
Maximum number of files to keep in search results. Results are filtered to include only chunks from the top N best-scoring files. For example, 1 returns only the single best-matching file's chunks. Unset means no file filtering.
Minimum chunk length in characters (1-10000, defaults to 50). Chunks shorter than this threshold are filtered out during ingestion.
Where to find authoritative docs and source for mcp-local-rag.
Open MCP Agent Studio and connect this server to Claude, GPT, Gemini, DeepSeek and more — no install required.
Open Agent Studio