io.github.sfrangulov/minirag-mcp MCP Server
io.github.sfrangulov/minirag-mcp
What is the io.github.sfrangulov/minirag-mcp MCP server?
Local-first RAG MCP server: hybrid search over a folder of your own documents
How to install io.github.sfrangulov/minirag-mcp
Copy-paste configuration for popular MCP clients.
BASE_DIROne document root; also the security boundary for file access. Defaults to the process working directory. Ignored when BASE_DIRS is set.
BASE_DIRSJSON array of document roots, e.g. ["/docs/a", "/docs/b"]. Takes precedence over BASE_DIR. An invalid value is a hard configuration error.
DB_PATHLanceDB index directory. Defaults to <first root>/.minirag/lancedb, so each corpus gets its own index.
CACHE_DIREmbedding model cache. Defaults to the platform user cache dir, so the ~220 MB model is downloaded once and shared.
MODEL_NAMEfastembed model id. Changing it makes existing vectors incompatible with new queries; pair with a new DB_PATH or a full re-ingest.
MAX_FILE_SIZEPer-file size limit in bytes, enforced before parsing.
CHUNK_TOKEN_BUDGETRetrieval-unit size in the embedding model's own tokens. Range 16-128; the ceiling is the model's trained sequence length.
RAG_HYBRID_WEIGHTKeyword weight in the weighted RRF fusion, range 0.0-1.0. 0 is vector-only; higher values raise the BM25 contribution.
RAG_GROUPINGResult grouping filter. 'similar' keeps only the closest group; 'related' also keeps the next one. Unset means no grouping filter.
RAG_MAX_DISTANCEDrop results whose vector distance exceeds this value. Lower is stricter. Unset means no distance filter.
RAG_MAX_FILESKeep chunks from at most this many best-scoring files. Unset means no per-file filter.
RAG_INSTRUCTIONS_APPENDExtra paragraph appended to the instructions the server hands the client at connect time, for corpus-specific guidance.
ALLOW_PRIVATE_URLSLet ingest_url fetch hosts resolving to loopback, link-local, private, reserved or unspecified addresses. Off by default.
Related MCP servers

s-gw
Local credential control for coding agents—approve bounded actions, keep secrets out of model context.
Esri ArcGIS Utility Network tools: trace, subnetworks, dirty areas, associations

MCP server for Azure Service Bus. Peek, search and replay dead-letter messages from any MCP client.

Enforce CLAUDE.md and .cursorrules as laws—block AI from breaking project constraints.
Persistent memory for AI coding agents—local SQLite + vector search, 19 MCP tools, zero cloud.

Native DevTools
AI-powered computer use for macOS, Windows, Android, and Chrome/Electron apps—screenshots, OCR, clicks, and element-precise automation.

