Log inSubmit server
Model Salt logo

Model Salt

Adds externally randomized creative decisions to MCP clients through one local tool, helping produce varied results from the same prompt.

InstallRepositoryWebsite
Get support Full README Compare alternatives Embed widget Claim this listing

Install Model Salt

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "model-salt": {
      "command": "npx",
      "args": [
        "-y",
        "@modelsalt/model-salt"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

Model Salt adds the `model_salt` tool to an MCP client so creative requests can receive randomized decisions before the model answers. It uses public randomness sources, including quantum-noise and beacon services, without sending prompts to them; offline runs use the computer's random generator. Use it for images, SVGs, writing, names, designs, plans, and other open-ended work where repeatability is less useful than controlled variation. The tool accepts a setting from 0 to 2 and can preserve selected decisions across later runs.

Use cases

  • Generate varied image and SVG directions
  • Develop alternate names, story openings, or design concepts
  • Explore multiple plans or approaches to an open-ended problem
  • Preserve selected creative decisions while revising a result

Key features

  • One MCP tool for randomized creative decisions
  • External randomness from quantum-noise and public beacon sources
  • Variation control from 0 to 2
  • Keeps selected decisions across subsequent runs
  • Local execution with offline random fallback
  • CLI setup and uninstall commands for supported clients

Tools1

What Model Salt lets your agent do. Expand a tool for its parameters.

Verified live~591 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

What it can do

From the 1 tool this server returned when we ran it; 1 declare their own safety hints.

Makes network requests · 1Read-only tools · 1
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age7 days
Maintainers1

Observed 2026-11-03 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 4d ago via OSV.dev · @modelsalt/model-salt (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars10Stargazers on the source repository.
npm downloads1kPackage downloads in the last 30 days.
Last commit1d agoMost recent push to the default branch.
MaintenanceActively maintainedStatus declared by the project or listing owner.
Tools exposed1Callable tools this server registers over MCP.

How Model Salt works

What Model Salt does

Model Salt changes how an MCP-compatible model approaches open-ended requests. Before producing a creative result, the model calls model_salt with the user's request and its own model name. The tool identifies important choices in the task, such as visual direction, tone, structure, or naming style, and returns decisions for the model to follow.

The result is intended to preserve the user's requirements while varying choices that could otherwise repeat across runs. Suitable requests include illustrations, SVGs, stories, poems, emails, designs, names, plans, and alternative approaches to a problem. Requests with one correct answer, such as factual questions, arithmetic, or a narrowly defined bug fix, are normally handled without the tool.

How it works

A separate short reasoning step identifies the largest open decisions and possible answers for each one. Random bytes from public sources select among those fitting answers; the user's prompt is not sent to those sources. The available sources include the LfD quantum random number service, drand, and NIST beacons. When the machine is offline, Model Salt uses its local random generator instead.

The model then completes the original request with the selected decisions. If an exploring step is returned, the model performs it silently and calls model_salt again with the step identifier and its full response. This can require additional model tokens and makes a salted response slower than an ordinary response.

A variation setting controls how strongly the usual model preference is retained. The range is 0 to 2: 0 keeps the usual choice, 1 is the default, and 2 distributes choices as evenly as the fitting options allow. Users can also ask to keep parts of an earlier result. The model passes those decisions in keep, so only the remaining choices are randomized.

Setup and configuration

Model Salt requires Node.js 18 or later, and npx downloads the package on its first use. The built-in setup commands add the server to a supported client's MCP configuration:

  • Claude Code: npx -y @modelsalt/model-salt setup claude
  • Codex: npx -y @modelsalt/model-salt setup codex
  • Gemini CLI: npx -y @modelsalt/model-salt setup gemini
  • Kimi Code: npx -y @modelsalt/model-salt setup kimi

Start a new client session after setup. --dry-run previews changes without applying them, and setup can be reversed with uninstall followed by the client name. Running setup again is safe. Gemini CLI requires the working folder to be trusted for local servers.

For manual configuration, run the stdio server with npx -y @modelsalt/model-salt anthropic for Claude, Gemini, and Kimi models, or npx -y @modelsalt/model-salt openai for GPT models. The shorter package name, model-salt, can also be used with npx.

Tools and capabilities

The server exposes one MCP tool:

  • model_salt: accepts the original request and the model name, then returns decisions to settle before the model completes the request. A follow-up call can include an exploration id and the model's response in explored.

The setup process can also add a short client skill for Codex and Kimi Code, and a startup visibility setting for Codex. Existing decisions can be retained with the keep field, while a fresh request can omit them.

Limitations and notes

Each salted response takes more time and tokens than a plain response. A documented example used roughly 3,300 additional output tokens per answer. If Claude Code or Codex is installed and signed in, the extra request can run through that local client and its plan. Otherwise, the active model performs the exploration through additional tool calls.

Model Salt runs locally and does not transmit prompts to its public randomness providers. It does depend on network access for those providers when online, although local randomness provides an offline fallback. The code is licensed under MIT; example runs and images use CC BY 4.0.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Model Salt

Model Salt is an MCP server that connects AI clients to external randomness sources and exposes the `model_salt` tool. It analyzes open choices in a creative request, selects decisions before generation, and lets the model produce varied results while preserving the original task and any choices marked to keep.

Run the client-specific `npx` setup command, such as `npx -y @modelsalt/model-salt setup claude` for Claude Code. Equivalent commands exist for Codex, Gemini CLI, and Kimi Code. Start a new session afterward; add `--dry-run` to preview changes.

Model Salt provides setup commands for Claude Code, Codex, Gemini CLI, and Kimi Code, and it can also be added manually as a stdio MCP server. The manual commands select an Anthropic-oriented or OpenAI-oriented model family.

Set the variation level in the prompt from 0 to 2, where 0 favors the model's usual choice, 1 is the default, and 2 spreads choices more evenly. You can also ask to keep particular decisions from an earlier result.

No, Model Salt does not send prompts to its public randomness providers. It requests random bytes from services such as LfD, drand, and NIST beacons; when offline, it uses the computer's own random generator.

Related MCP servers

All in Art & Culture All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewModel Salt AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/model-salt?style=directory)](https://allmcps.com/mcp/model-salt)
HTML Embed
<a href="https://allmcps.com/mcp/model-salt"><img src="https://allmcps.com/api/badge/model-salt?style=directory" alt="Model Salt on AllMCPs" /></a>