pickfit

BrowseMCP servers

Brain OS

Local-first MCP server that stores project decisions, blockers, plans and priorities across sessions.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Node.js 20 or newer
  • Keys or accounts: OPENAI_API_KEY
  1. Install brain-os globally via npm

    npm install -g brain-os

Add it to your agent

claude mcp add brain-os -- brain-os serve
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "brain-os": {
      "command": "brain-os",
      "args": [
        "serve"
      ]
    }
  }
}

Run brain-os init <folder> in your project folder, then add brain-os serve as an MCP server in your MCP client.

What it does

  • Track projects with status and blockers
    How to use it
    1. Run brain-os init <folder> in your project folder.
    2. Connect your MCP client to brain-os serve.
    3. Call the entity_update tool with a project ID and its status, blockers and next moves.
    Tested
  • Check a proposed action against active decisions
    How to use it
    1. Run brain-os init <folder> in your project folder.
    2. Connect your MCP client to brain-os serve.
    3. Call the decision_check tool with your proposed action and the project ID.
    Tested
  • Get prioritized recommendations on what to work on
    How to use it
    1. Run brain-os init <folder> in your project folder.
    2. Connect your MCP client to brain-os serve.
    3. Call the focus_get tool with no arguments.
    Tested
  • Log decisions with the alternatives you rejected
    Not tested

How far pickfit got

Linux x86_64

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

Good for

  • check a proposed action against logged decisions
  • log strategic decisions with reasoning and rejected alternatives
  • get prioritized recommendations on what to work on
  • search project memory by meaning
  • save session state changes at end of session

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 31 Oct 2026
  • Version 0.11.0

An MCP client handshake over stdio listed 24 tools, and a call to entity_update returned a result.

Differences the test machine hit

  • README: npm install brain-os openai for semantic search
    In the test: global install npm install -g brain-os required for probe; npx launcher would fetch on each run and fail offline

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.