pickfit

BrowseMCP servers

Model Salt

MCP server that adds outside randomness so one prompt yields varied answers that still follow the request.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Node 18 or later
  1. install model-salt globally via npm

    npm install -g @modelsalt/model-salt

Check that it works

model-salt --help 2>&1

The output should contain “Model Salt 1.0.1”.

Add it to your agent

claude mcp add model-salt -- model-salt anthropic
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "model-salt": {
      "command": "model-salt",
      "args": [
        "anthropic"
      ]
    }
  }
}

Add Model Salt as an MCP server in your MCP client, then ask the assistant to use the model_salt tool when you want varied answers.

What it does

  • Get different answers from the same prompt
    Not shown working
  • Generate varied pictures, names and stories
    Not shown working
  • Set how strong the variation is, from 0 to 2
    Not shown working

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 0 of 3 features work
  4. Works offline

Good for

  • Generate an SVG of a pelican riding a bicycle
  • Suggest a name for a neighbourhood coffee shop
  • Write the first line of a short story about a lighthouse keeper

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 1 Nov 2026
  • Version 1.0.1

An MCP client handshake over stdio listed 1 tool, and a call to model_salt returned a result.

Differences the test machine hit

  • README: Each call runs one short extra request through Claude Code/Codex (signed in)
    In the test: Without sign-in the tool returns fallback 'The random step could not run this time, so nothing was settled. Carry on with the request as asked.' but still exits 0 and handshake/tool call succeed

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.