pickfit

BrowseMCP servers

minirag-mcp

Local-first RAG MCP server giving hybrid search over your own documents.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Python 3.11+
  • System packages: uv
  1. install minirag-mcp with uv tool

    uv tool install minirag-mcp
Where the README and reality differ
  • README: `query_documents` and `list_files` take `labels`, `dateFrom` and `dateTo`
    What worked: any labels/dateFrom/dateTo filter is refused without <root>/.minirag/classify.toml, even a date-only filter; created minimal default-facet taxonomy to make it answer
  • README: `find_mentions` lists every document that mentions a phrase
    What worked: installed PyPI v1.0.0 exposes 11 MCP tools with no find_mentions; README describes 12 tools including find_mentions

Check that it works

minirag-mcp --version

The output should contain “1.0.0”.

Add it to your agent

claude mcp add minirag-mcp -e BASE_DIR='<BASE_DIR>' -- minirag-mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "minirag-mcp": {
      "command": "minirag-mcp",
      "args": [],
      "env": {
        "BASE_DIR": "<BASE_DIR>"
      }
    }
  }
}

You fill in

  • BASE_DIR: folder you want indexed (required)

Ask the user for BASE_DIR; pickfit never had a value, so these are placeholders.

Index a folder first with minirag-mcp sync --base-dir <folder>, then add minirag-mcp as a server in your MCP client with BASE_DIR set to that folder.

What it does

  • Search your local documents by meaning and keyword
    How to use it
    1. Index your folder with minirag-mcp sync --base-dir <folder>.
    2. Start minirag-mcp from your MCP client with BASE_DIR set to <folder>.
    3. Call the query_documents tool with your query and an optional topK, such as {"query":"<your text>","topK":5}.
    Tested
  • Add documents in 12 file formats
    How to use it
    1. Start minirag-mcp from your MCP client with BASE_DIR set to your documents folder.
    2. Call the ingest_data tool with your content, a source name and a format, such as {"data":"<your text>","source":"<name>","format":"markdown"}.
    Tested
  • List every document that mentions a phrase
    Not tested
  • Filter search results by labels and dates
    Not shown working

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 2 of 4 features work
  4. Works offline

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • search documents with hybrid semantic and keyword search
  • list every document containing a word or phrase
  • index a folder of documents for RAG

An alternative to shinpr/mcp-local-rag.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 1.0.0

An MCP client handshake over stdio listed 11 tools, and a call to query_documents returned a result.

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.