Minirag MCP server

by sfrangulov·io.github.sfrangulov/minirag-mcp·v0.6.1

No reviews yet

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

A92/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A92/100

full report

Adoption

Growing

68 stars

Reviews

Write one

Nobody has reviewed Minirag yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Minirag tools (11, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

delete_filewrite action
Delete an indexed file, data item, or url item from the index.
ingest_data
Ingest text/markdown/html content the client holds, under a source id you choose.
ingest_file
Ingest or re-ingest one file, replacing any content already indexed for it.
ingest_url
Fetch an http(s) URL, convert it to Markdown, and index it.
list_files
List files found on disk under the document roots, plus indexed data/url sources.
query_documents
Hybrid search: semantic similarity plus a keyword boost for exact terms.
read_chunk_neighbors
Read the chunks immediately before and after a search result, for context.
read_file
Read a source's entire indexed content as Markdown.
status
Report configuration and index status. Works even when configuration is invalid.
sync_start
Reconcile the index with the document roots (or one path inside them).
sync_status
Poll a sync job started by sync_start.

Public scan report

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

no findings

Code scan29 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 13 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Install directly

claude mcp add minirag-mcp -- uvx minirag-mcp

Add to Cursor

Minirag: common questions

Is Minirag MCP server safe?: Yes, by our scan: it is graded A (92/100). Read the Minirag safety report
How do I install Minirag?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Minirag need an API key?: No secret keys are declared. It reads 13 settings from the environment.
Is Minirag maintained?: The last commit was 13 days ago (2026-09-07). The latest release is v0.6.1.
What can I use instead of Minirag?: Servers from other publishers that do the same job: PDF MCP server, haiku.rag MCP server and Linksee Memory MCP server. Compare all Minirag alternatives.

Alternatives to Minirag

Same job from other publishers: the closest match first, then the best rated.

All Minirag alternatives →

PDF
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
not reviewed
Established
A
haiku.rag
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
not reviewed
Established
A
Linksee Memory
Hand a project over with the reasons attached. Local-first cross-agent memory MCP + drift detection.
not reviewed
Growing
A
Agent-Native Chat
Minimal chat-first app with durable threads, actions, and the app-agent loop
not reviewed
Established
A
Local Rag
Easy-to-setup local RAG server with minimal configuration
not reviewed
Established
A

Minirag vs PDF Minirag vs haiku.rag Minirag vs Linksee Memory

Run it through the gateway

Local package. It runs on your machine, not through the gateway.

Rating: —
Safety grade: A · 92/100
Stars: 68
Downloads/wk: –
Price: Free
Licence: MIT
Transport: Local · pypi
Version: 0.6.1
Category: AI and agents
Last release: 2026-09-07

Credentials it needs

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.

Own this server?

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Claim listing

Badge for your README

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/sfrangulov-minirag-mcp.svg)](https://mcp.market/server/sfrangulov-minirag-mcp)

How the badge works