pickfit

BrowseMCP servers

RuvNet Brain

Source-grounded companion that helps Claude Code and Codex discover and use RuvNet ecosystem source.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Node.js 18 or newer
  1. global npm install of ruvnet-brain package

    npm install -g ruvnet-brain@latest
  2. run installer to fetch signed knowledge bundle and models

    ruvnet-brain --yes --no-nightly-prompt --no-telemetry --no-stack --no-enhance --no-statusline --no-selfcheck
Where the README and reality differ
  • README: npx ruvnet-brain@latest installs in one step
    What worked: run installer after npm install: ruvnet-brain --yes --no-nightly-prompt --no-telemetry --no-stack --no-enhance --no-statusline (fetches 1.5GB KB + 257MB models); until then --doctor reports brain not found

Check that it works

ruvnet-brain --help

The output should contain “It is safe to re-run at any time”.

First thing to try

ruvnet-brain --doctor

Add it to your agent

claude mcp add ruvnet-brain -- node $HOME/.local/lib/node_modules/ruvnet-brain/plugin/mcp/server.mjs
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "ruvnet-brain": {
      "command": "sh",
      "args": [
        "-c",
        "exec node \"$HOME/.local/lib/node_modules/ruvnet-brain/plugin/mcp/server.mjs\""
      ]
    }
  }
}

Run ruvnet-brain --doctor to check the setup, then use the search_ruvnet tool from Claude Code or Codex.

What it does

  • Ask in plain language which RuvNet tools fit a need
    How to use it
    1. In Claude Code or Codex, call the search_ruvnet tool.
    2. Pass your question as the query, such as "<your question>".
    3. Read the text answer listing matching RuvNet options.
    Tested
  • Search source code with repository citations
    Not shown working
  • Keep useful project context to recall later
    Not tested

How far pickfit got

Linux x86_64

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

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

Good for

  • Show how Ruflo coordinates agents with implementing source
  • Show how RVF stores and queries vectors with source citations
  • Compare RuvNet approaches for routing model calls
  • Review a project agent workflow and propose smallest verifiable change
  • Find RuvNet options for persistent agent memory

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 4.7.23

An MCP client handshake over stdio listed 4 tools, and a call to search_ruvnet returned a result.

Differences the test machine hit

  • README: installer exits 0 after successful install
    In the test: add --no-selfcheck for exit 0 on a machine with no Claude Code/Codex plugin; without it installer exits 1 with no-plugin hooks violation even though Knowledge checks are green
  • README: standard --version prints tool version
    In the test: ruvnet-brain --version requires a release tag (e.g. --version vX.Y.Z) and exits 1; use ruvnet-brain --help / --doctor and read version 4.7.23 from package.json

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.