pickfit

BrowseLocal AI tools

brainstorm-mcp

MCP server that runs multi-round debates between AI models and returns a synthesis.

Use it

Before you install: known vulnerabilities

pickfit found 1 known high or critical vulnerability in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • npm:zod 3.25.76 Zod can exhaust memory while validating oversized constrained collections (GHSA-mrhx-c7xc-m3w5, high, fixed in 4.6.6)

Linux x86_64

  1. Install brainstorm-mcp via npm global

    npm install -g brainstorm-mcp
Where the README and reality differ
  • README: brainstorm-mcp runs as a command with --help/--version style checks
    What worked: binary ignores --help/--version and starts MCP server on stdio ('Brainstorm MCP server running on stdio'), waiting on stdin; verify via MCP initialize/tools/list handshake instead
Verified in pickfit: the commands exactly as its sandbox ran them

For the record only: they name the sandbox's home, /home/sbx.

npm install -g brainstorm-mcp
npm ls -g brainstorm-mcp && node -p "require('/home/sbx/.local/lib/node_modules/brainstorm-mcp/package.json').version"
npm ls -g brainstorm-mcp && node -p "require('/home/sbx/.local/lib/node_modules/brainstorm-mcp/package.json').version"

Check that it works

npm ls -g brainstorm-mcp && node -p "require('$HOME/.local/lib/node_modules/brainstorm-mcp/package.json').version"

The output should contain “brainstorm-mcp@1.8.0”.

First thing to try

npm ls -g brainstorm-mcp && node -p "require('$HOME/.local/lib/node_modules/brainstorm-mcp/package.json').version"

Add brainstorm-mcp as a stdio MCP server in your MCP client, then call its list_providers tool to see which models are available.

What it does

  • Run multi-round debates between AI models
    How to use it
    1. Call the brainstorm tool with a topic, a list of models, the number of rounds and a style.
    2. Pass each model's answer back with the brainstorm_collect tool, using the session_id from the first reply.
    Tested
  • Get a three-part synthesis verdict
    How to use it
    1. Start a debate with the brainstorm tool and send the model responses with brainstorm_collect.
    2. Send the synthesis response with brainstorm_collect to get the Recommendation, Key Tradeoffs and Strongest Disagreement sections.
    Tested
  • Get quick views from several models
    Not tested
  • Review code with several models and get verdicts
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  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

  • compare Redis vs PostgreSQL for session storage
  • review a diff for security issues
  • debate whether to use GraphQL or REST

How pickfit tested it

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

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 1.8.0

Differences the test machine hit

  • README: Hosted mode needs zero API keys
    In the test: hosted brainstorm + brainstorm_collect full loop works with no keys; brainstorm_quick and brainstorm_review return 'Need at least 1 model configured' unless an API key or CLI provider is set

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.