FRENES

Files and documents · MCP server

Minirag MCP: MCP server, setup and security

Minirag MCP is an open-source MCP server published on GitHub that lets an AI agent perform hybrid searches over a folder of local documents. Its repository has 58 stars and its last commit is from October 23, 2026 and it is licensed under MIT.

Actively maintainedSystem access

What Minirag MCP does

According to its repository: “Local-first RAG MCP server: hybrid search over a folder of your own documents”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Minirag MCP is listed under Files and documents, a category of 55 servers in the directory, where it ranks #28 by stars.

Topics declared by the repository: bm25, claude-code, embeddings, fastembed, fastmcp, hybrid-search.

Installing and connecting Minirag MCP

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

Points found for Minirag MCP:

  • System access: the Files and documents category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on August 7, 2026, the sfrangulov/minirag-mcp repository has 58 stars and 2 forks, with 0 open issues. It has more stars than 54% of the servers in the directory. It received changes this month. Version published in the registry: 1.0.0 (October 22, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

MarkitdownMarkitdown : 191.9K191.9KPuterPuter : 43.9K43.9KFilestashFilestash : 14.8K14.8KRevoGrid DataGrid MCPRevoGrid DataGrid MCP : 3.5K3.5KDocling MCPDocling MCP : 777777MCP filesystem serverMCP filesystem server : 692692Haiku.ragHaiku.rag : 636636MuMu : 436436Minirag MCPMinirag MCP : 5858
GitHub stars of the most followed servers in the category (log scale); Minirag MCP in orange. Checked October 25, 2026.

Verdict

Minirag MCP is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Avoid if…

  • You cannot isolate the agent (sandbox, container)

Frequently asked questions

How do I install Minirag MCP?

Minirag MCP is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of sfrangulov/minirag-mcp.

Is Minirag MCP free?

The code is published under the MIT licence and can be used free of charge.

Is Minirag MCP safe?

Points to watch: system access. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by sfrangulov on GitHub. Check who maintains it before giving it access.

What are the alternatives to Minirag MCP?

In the same category: Markitdown, Puter, Filestash, and RevoGrid DataGrid MCP. Markitdown and Puter score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score