Home › Search & Research › minirag-mcp
minirag-mcp
Local-first RAG MCP server: hybrid search over a folder of your own documents
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (pypi 0.6.1)
uvx minirag-mcp
Or add to your MCP client config:
{
"mcpServers": {
"minirag-mcp": {
"command": "uvx",
"args": [
"minirag-mcp"
],
"env": {
"BASE_DIR": "<YOUR_VALUE>",
"BASE_DIRS": "<YOUR_VALUE>",
"DB_PATH": "<YOUR_VALUE>",
"CACHE_DIR": "<YOUR_VALUE>",
"MODEL_NAME": "<YOUR_VALUE>",
"MAX_FILE_SIZE": "<YOUR_VALUE>",
"CHUNK_TOKEN_BUDGET": "<YOUR_VALUE>",
"RAG_HYBRID_WEIGHT": "<YOUR_VALUE>",
"RAG_GROUPING": "<YOUR_VALUE>",
"RAG_MAX_DISTANCE": "<YOUR_VALUE>",
"RAG_MAX_FILES": "<YOUR_VALUE>",
"RAG_INSTRUCTIONS_APPEND": "<YOUR_VALUE>",
"ALLOW_PRIVATE_URLS": "<YOUR_VALUE>"
}
}
}
}
BASE_DIR— One document root; also the security boundary for file access. Defaults to the process working directory. Ignored when BASE_DIRS is set.BASE_DIRS— JSON array of document roots, e.g. ["/docs/a", "/docs/b"]. Takes precedence over BASE_DIR. An invalid value is a hard configuration error.DB_PATH— LanceDB index directory. Defaults to <first root>/.minirag/lancedb, so each corpus gets its own index.CACHE_DIR— Embedding model cache. Defaults to the platform user cache dir, so the ~220 MB model is downloaded once and shared.MODEL_NAME— fastembed model id. Changing it makes existing vectors incompatible with new queries; pair with a new DB_PATH or a full re-ingest.MAX_FILE_SIZE— Per-file size limit in bytes, enforced before parsing.CHUNK_TOKEN_BUDGET— Retrieval-unit size in the embedding model's own tokens. Range 16-128; the ceiling is the model's trained sequence length.RAG_HYBRID_WEIGHT— Keyword weight in the weighted RRF fusion, range 0.0-1.0. 0 is vector-only; higher values raise the BM25 contribution.RAG_GROUPING— Result grouping filter. 'similar' keeps only the closest group; 'related' also keeps the next one. Unset means no grouping filter.RAG_MAX_DISTANCE— Drop results whose vector distance exceeds this value. Lower is stricter. Unset means no distance filter.RAG_MAX_FILES— Keep chunks from at most this many best-scoring files. Unset means no per-file filter.RAG_INSTRUCTIONS_APPEND— Extra paragraph appended to the instructions the server hands the client at connect time, for corpus-specific guidance.ALLOW_PRIVATE_URLS— Let ingest_url fetch hosts resolving to loopback, link-local, private, reserved or unspecified addresses. Off by default.
Related servers
Sui Knowledge Base (kapa.ai)
Semantic search across Sui documentation and knowledge sources, powered by kapa.ai
wigolo
Local-first web intelligence MCP server for AI coding agents
Zotero MCP
Search, read, annotate, and add to your Zotero research library, local or web.
exa-mcp-server
Connect AI agents to Exa for web search, content fetching, and multi-step research.
arxiv-mcp-server
Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
trieve
Crawl, embed, chunk, search, and retrieve information from datasets through [Trieve](https://trieve.ai)
Data from the Official MCP Registry