Minirag MCP Server

by sfrangulovio.github.sfrangulov/minirag-mcpv0.6.1

Local-first RAG MCP server: hybrid search over a folder of your own documents

67Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Maintained32d ago

Install Minirag MCP server

claude mcp add minirag -- uvx minirag-mcp

{
  "mcpServers": {
    "minirag": {
      "command": "uvx",
      "args": [
        "minirag-mcp"
      ]
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "minirag": {
      "command": "uvx",
      "args": [
        "minirag-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "minirag": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "minirag-mcp"
      ]
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "minirag": {
      "command": "uvx",
      "args": [
        "minirag-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
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.