Model Salt

com.modelsaltPublished by modelsalt.comOfficial publisherv1.0.4Updated Nov 5, 2026

Randomness from outside the model, so one prompt gives different answers that still fit the ask.

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Model Salt injects outside randomness into creative prompts so an assistant's answers vary between runs while still fitting the request.

What you can do
  • Call the model_salt tool with a request word for word to get back the open decisions to settle this time
  • Run a second call with the returned id and the assistant's reply to complete the exploring step
  • Adjust how far results stray from the model's usual pick with a 0 to 2 setting (default 1)
  • Carry chosen answers forward through a keep field so only the remaining open choices are re-rolled
  • Skip the tool for questions with a single right answer, such as sums, facts or bug fixes
When to use it
Useful when you want genuinely different outputs from repeated runs of the same open-ended prompt: images, SVGs, names, stories, plans or designs. Not intended for factual or single-answer tasks, where the model is told to skip it.
Requirements
Node 18 or later for the npx package, or the remote endpoint. Setup commands add the server to Claude Code, Codex, Gemini CLI or Kimi Code. Optionally a signed-in Claude Code or Codex install, which runs one short extra request on your own plan; without one, the model does that step in its own chat and uses more tokens. Network access for public randomness sources, with a local fallback offline.
Before you install
Setup writes to your client's MCP configuration and, for Codex and Kimi Code, adds a skill under ~/.agents/skills/; uninstall removes it. Salted answers take longer and use more tokens (about 3,300 extra output tokens per answer in one example). Prompts are not sent to the randomness sources, and nothing is stored server-side, but the tool does change how the assistant answers.

Installation

In SourceWeft

  1. Open Model Salt in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.modelsalt%2Fmodel-salt/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "model-salt": {
      "type": "http",
      "url": "https://modelsalt.com/mcp"
    }
  }
}

README

Model Salt

Ask a language model for the same thing ten times and you get the same answer ten times. Model Salt is an MCP server that gives your model randomness from outside it, so one prompt gives ten different answers that still do exactly what you asked.

[npm] [MIT licence]

modelsalt.com · works in Claude Code, Codex, Gemini CLI and Kimi Code

[Ten runs of "Generate an SVG of a pelican riding a bicycle" on Claude Opus 5.5: the plain prompt draws the same pelican ten times, with Model Salt nine of the ten pictures are different]

Install

One command adds it to your client. Run it once.

ClientCommand
Claude Codenpx -y @modelsalt/model-salt setup claude
Codexnpx -y @modelsalt/model-salt setup codex
Gemini CLInpx -y @modelsalt/model-salt setup gemini
Kimi Codenpx -y @modelsalt/model-salt setup kimi

Start a new session in your client after it, and the model_salt tool is there.

  • What it adds: the model-salt server in your client's MCP list. For Codex and Kimi Code it also adds a short skill at ~/.agents/skills/model-salt/ that tells the model when to call the tool, and for Codex one setting on that server so the model sees the tool from the start.
  • Gemini CLI runs local servers only in folders you trust.
  • See first: add --dry-run to print what it would change and change nothing.
  • Run it twice: nothing changes the second time.

Undo

sh
npx -y @modelsalt/model-salt uninstall claude    # or codex, gemini, kimi

It takes out everything setup added. The skill stays while another client of yours still uses it. --dry-run works here too.

Use it

Ask for anything with room for choices: a picture, an SVG, a page, a name, a story, a plan. The model calls model_salt with your request, gets back what to settle this time, and then does your request as you asked it.

Want more or less of it? Say so in your prompt ("make it really different", "keep it close to the usual"). The tool takes a setting from 0 to 2. Left out, it is 1.

SettingHow often each choice keeps the model's usual pick (target)
0always
0.570% of the time
1 (default)45% of the time
1.525% of the time
2no more often than any other fitting pick

The model skips the tool for questions with one right answer (a sum, a fact, a bug fix).

Keep what you like. Like part of a result? Say what to keep in plain words ("keep the palette and layout, give me new illustrations"). Your model copies those decided answers from the earlier Model Salt reply into the tool's keep field and calls it again. Only the open choices are rolled again, and the reply starts with one line, e.g. Kept: palette = burnt orange on cream; layout = split screen, text left. That holds on later runs until you say start fresh, and "give me something new" leaves it out. In a new chat, paste the Kept: line or say it in your own words. A kept answer that no longer fits a new request is dropped, and the reply says so. Nothing is stored on our side.

What it changes

Same prompt, 10 runs each, from the examples on modelsalt.com.

"Generate an SVG of a pelican riding a bicycle." Different pictures in 10 runs:

ModelPlain promptWith Model Salt
Claude Opus 5.519
Claude Fable 5.139
GPT-6.1 Sol210
GPT-6 Astra18
Gemini 4 Argon210
Kimi K319

"Suggest a name for a neighbourhood coffee shop." Claude Opus 5.5, the first five runs:

Plain promptWith Model Salt
The Common GrindThe Footbridge
Common GroundBrew Espresso Bar
The Common GrindSnugwick Corner
The Daily Grind & GatherOld Oak's
The Common CupHilltop Coffee

"Write the first line of a short story about a lighthouse keeper." Claude Opus 5.5:

  • Plain, 5 of 5 runs: "For thirty-one years, Elias Marrow had kept the light burning for ships that never..." (Marrow, Maren or Marsh, thirty-one or forty-one years)
  • With Model Salt: "The sea has gone perfectly still, and I have never been more afraid." / "The beam swept the black water again, lighting nothing Tomas had ever loved." / "Halfway up the iron stair with a can of whale oil knocking against her knee, Agnes Merrow..."

Every run, plain and salted, is in examples/, with the prompt, the model and the answer.

What it needs

  • Node 18 or later. npx fetches the package the first time.
  • Claude Code or Codex, signed in, or neither. With one of them on the machine, each call runs one short extra request on your machine, on your own plan, with no API key: through Codex when you use Codex, and through Claude Code (Claude Opus 5.5) when you use Claude Code, Gemini CLI or Kimi Code. If that request can't run (signed out), the tool says so and your model carries on with the request as asked. With neither on the machine (a Docker container, Cursor or Copilot alone), your own model does that step in its own chat: it calls the tool twice, first with the request, then with its reply to the exploring step, and uses more of its own tokens for it.
  • Time and tokens. A salted answer takes longer and uses more tokens than a plain one. On the pelican prompt, Claude Opus 5.5 used about 3,300 more output tokens per answer.
  • Network. The server fetches random bytes from public randomness sources (quantum noise from the LfD quantum random number service, and the public drand and NIST beacons). Your prompt is not sent to them. Offline, it uses your computer's own random generator.

Other ways to run it

  • Short name: npx -y model-salt <args> runs the same package as npx -y @modelsalt/model-salt <args>.
  • As a plugin: plugin/ holds a Codex plugin, a Claude Code plugin and a Gemini CLI extension, and this repo is a plugin marketplace. From a clone:
    • Codex: codex plugin marketplace add /path/to/model-salt, then codex plugin add model-salt@model-salt
    • Claude Code: claude plugin marketplace add /path/to/model-salt, then claude plugin install model-salt@model-salt
    • Gemini CLI: gemini extensions install /path/to/model-salt/plugin
  • By hand: add a stdio MCP server that runs npx -y @modelsalt/model-salt anthropic (Claude, Gemini and Kimi models) or npx -y @modelsalt/model-salt openai (GPT models).
  • From a clone: node src/stdio.mjs anthropic in place of the npx command.

How it works

In a separate short run (with no Claude Code or Codex on the machine, in your own model's chat, over two tool calls), the model names the biggest open decisions in your request (the questions an expert would ask) and a range of answers to each, its usual one included. Randomness from outside the model picks one answer per question. Your model then does the request with those answers settled. More, and why simpler ways failed: docs/how-it-works.md.

Contributing

Found a prompt that still gives the same answer every time with Model Salt? Open an issue with the prompt, the model and a few runs. How to test a change to a family's steps: CONTRIBUTING.md.

Privacy

Model Salt runs on your machine and never sends your prompts anywhere. It only asks public random sources for random bytes. Details: Privacy policy.

Licence

  • Code: MIT, see LICENSE.
  • Example runs and pictures (examples/, the images in docs/): CC BY 4.0, credit "Model Salt", see examples/LICENSE.
  • Word list (src/words.mjs, Webster's 2nd, 1934): public domain.

Model Salt is a project by Chris Benjaminsen.

Source: README.md at commit 61b3712

Tools

1

model_salt

Model Salt

Call this before any creative or open-ended request (an image, a picture prompt, a story, a poem, a name, an idea, a design, a plan), so the result is varied instead of your usual answer and still exactly what was asked. First call: send the user's request word for word in `request` (and `randomness` only if the user asked for more or less variety). It returns an exploring step and an `id`. Do that step silently, without showing it to the user, and call this tool again with the `id` and your whole reply to the step in `explored`. The second call returns what was decided. Then make the result itself in the same reply: for a request for an image, generate the image with your image generation tool and show it (a written prompt is not the result); for writing, write it. The result shows every decided answer.

Parametersidkeeprequestexploredrandomness

Version history

3
  1. v1.0.4LatestNov 5, 2026
  2. v1.0.2Nov 3, 2026
  3. v1.0.1Oct 29, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts