mcp-local-rag

Easy-to-setup local RAG server with minimal configuration

stdio v0.8.0

Connection Configuration

Add this to your AI agent's MCP config file to connect.

Run in your terminal:

claude mcp add io.github.shinpr--mcp-local-rag -- npx

Transport

stdio

Authentication

None

Version

v0.8.0

Server Name

io.github.shinpr/mcp-local-rag

Last Updated

Mar 7, 2026

How to install and connect this MCP server.

Environment variables you must provide when running this server.

Variable	Description	Required
`BASE_DIR`	Base directory for document storage (defaults to current working directory)	Optional
`DB_PATH`	Path to LanceDB database directory (defaults to ./lancedb/)	Optional
`CACHE_DIR`	Directory where Transformers.js models are cached (defaults to ./models/)	Optional
`MODEL_NAME`	Embedding model name (defaults to Xenova/all-MiniLM-L6-v2)	Optional
`MAX_FILE_SIZE`	Maximum file size in bytes (defaults to 104857600 / 100MB)	Optional
`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)	Optional
`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	Optional
`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.	Optional