Model Salt

Name: Model Salt
Author: modelsalt

作者：modelsalt版本 1.0.4i★ –i电脑或云端

注册名称com.modelsalt/model-salt

安装

概览

作者提供的说明（英文原文）

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

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i3 项中通过 3 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 电脑或云端
传输方式: stdio, Streamable HTTP
分类: 其他

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：3 项中通过 3 项
在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
可以做 1 件事（工具） model_salt
注册中心没有列出需要填写的密钥。

你需要

在云端运行无需安装任何东西，通过互联网连接
npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude：

打开 Settings → Connectors
点击 Add custom connector
粘贴下面的地址，然后点击 Add
如果要求登录，请登录作者的服务

https://modelsalt.com/mcp

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "model-salt": {
      "command": "npx",
      "args": [
        "-y",
        "@modelsalt/model-salt",
        "anthropic"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add --transport http model-salt https://modelsalt.com/mcp

或者在你的电脑上运行

claude mcp add model-salt -- npx -y @modelsalt/model-salt anthropic

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

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

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "model-salt": {
      "command": "npx",
      "args": [
        "-y",
        "@modelsalt/model-salt",
        "anthropic"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

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

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "model-salt": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelsalt/model-salt",
        "anthropic"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

ChatGPT 只能连接互联网上的服务器：

打开网页版 ChatGPT → Settings → Connectors (Apps)
点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
粘贴下面的地址，起个名字，然后保存
如果要求登录，请登录作者的服务

https://modelsalt.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月6日报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

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 `reque

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

✓ 通过
作者与仓库一致
注册名称已通过域名 modelsalt.com 验证（注册中心会核实域名所有权）
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
✓ 通过
端点有响应
在 1132 毫秒内响应（HTTP 200）
– 不适用
使用 OAuth 登录
无需登录
✓ 通过
工具描述中没有隐藏指令
已读取 1 个工具描述，未发现针对 AI 的隐藏指令

与“其他”中的其他服务器比较i

星标数多于此分类中其他 32464 个服务器的 0%
发布到注册中心的时间比此分类中其他 32464 个服务器的 96% 更新
基础检查结果等于或优于此分类中其他 32464 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Model Salt 安全吗？

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

两种方式都可以：安装在你的电脑上，或者连接云端版本。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（1.0.4）于昨天进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：Spec Driven Development, Remote Desktop Commander, yontu

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新

安装

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新

安装

yontu

作者：senrecep

Türkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup.

在你的电脑上运行今天更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

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.

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

Install

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

Client	Command
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 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

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.

Setting	How often each choice keeps the model's usual pick (target)
0	always
0.5	70% of the time
1 (default)	45% of the time
1.5	25% of the time
2	no 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:

Model	Plain prompt	With Model Salt
Claude Opus 5.5	1	9
Claude Fable 5.1	3	9
GPT-6.1 Sol	2	10
GPT-6 Astra	1	8
Gemini 4 Argon	2	10
Kimi K3	1	9

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

Plain prompt	With Model Salt
The Common Grind	The Footbridge
Common Ground	Brew Espresso Bar
The Common Grind	Snugwick Corner
The Daily Grind & Gather	Old Oak's
The Common Cup	Hilltop 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 runs the same package as npx -y @modelsalt/model-salt .
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.

Model Salt

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

或者在你的电脑上运行

或者在你的电脑上运行

或者在你的电脑上运行

或者在你的电脑上运行

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“其他”中的其他服务器比较i

常见问题

替代选择

Spec Driven Development

Remote Desktop Commander

yontu

作者的 README

Model Salt

Install

Undo

Use it

What it changes

What it needs

Other ways to run it

How it works

Contributing

Privacy

Licence