MCP ServerSTDIOOfficialv0.12.0

mcp-local-rag MCP Server

Easy-to-setup local RAG server with minimal configuration

io.github.shinpr/mcp-local-rag

Hosted URL

https://github.com/shinpr/mcp-local-rag

Transport

STDIO

Auth

No auth required

Connect to mcp-local-rag

Hosted endpoint — paste into any MCP client.

https://github.com/shinpr/mcp-local-rag

Environment variables

Configuration this server reads at startup.

  • BASE_DIR

    Base directory for document storage (defaults to current working directory)

  • DB_PATH

    Path to LanceDB database directory (defaults to ./lancedb/)

  • CACHE_DIR

    Directory where Transformers.js models are cached (defaults to ./models/)

  • MODEL_NAME

    Embedding model name (defaults to Xenova/all-MiniLM-L6-v2)

  • MAX_FILE_SIZE

    Maximum file size in bytes (defaults to 104857600 / 100MB)

  • RAG_MAX_DISTANCE

    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)

  • RAG_GROUPING

    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

  • RAG_MAX_FILES

    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.

  • CHUNK_MIN_LENGTH

    Minimum chunk length in characters (1-10000, defaults to 50). Chunks shorter than this threshold are filtered out during ingestion.

Resources

Where to find authoritative docs and source for mcp-local-rag.

Try mcp-local-rag with 30+ AI models

Open MCP Agent Studio and connect this server to Claude, GPT, Gemini, DeepSeek and more — no install required.

Open Agent Studio

Related servers

More on MCP Playground