TypoSafe AI — Jef

lol.typosafe由 typosafe.lol 发布官方发布者v0.4.7更新于 Oct 24, 2026

Jef decides. Give it options, it returns one with a confidence, never a sentence. A parody.

已验证Streamable HTTP可网页运行

概览

AI 生成的概览

一个恶搞性质的决策服务器,不生成文本,而是返回任意的是/否、选项、评分、排序或标记,并附带置信度。

可以做什么
提出一个是非问题,得到 YES 或 NO,并附带置信度和结构化内容,其中包含升级与拦截标记,助手应按其处理而不是换个问法重试。
适用场景
当你想要一个刻意任意但可重复的决定——在几个选项中选一个、打 1 到 10 分、排序,或给出红旗/绿旗/米色旗——并且清楚这只是玩笑、不是建议时使用。
运行要求
可以使用托管远程端点,无需安装、密钥或账号;也可以本地运行 npm 包 jef-mcp(stdio),需要 Node.js 和 npx,本地版本完全离线且无依赖。
安装前请注意
答案刻意任意,不得当作建议呈现;涉及健康、伤害、金钱、法律或安全的问题会返回转交人工,含脏话、侮辱或性内容的输入会返回未评估,且不应重试。

安装

在 SourceWeft 中

  1. 打开 控制台中的 TypoSafe AI — Jef,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/lol.typosafe%2Fjef/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "typosafe-ai-jef": {
      "type": "http",
      "url": "https://typosafe.lol/mcp"
    }
  }
}

README

Jef MCP

An MCP server for a model that decides instead of generating.

Jef never produces text. Every answer is one of the options you supplied, a number from 1 to 10, a yes or no, or a flag, with a confidence between 84% and 99%. It reads 0 tokens of your input, because it hashes it rather than reading it. It stores nothing, costs nothing, and returns the same answer for the same input forever.

It is a parody of TypeSafe AI's real decision model, Jev, and it is labelled as one everywhere. If you want to understand the real thing, we wrote a straight explainer for it: What is Jev?

Connect

The server is hosted. Nothing to install, no key, no account.

https://typosafe.lol/mcp

Claude Code:

bash
claude mcp add --transport http jef https://typosafe.lol/mcp

Anything that reads a config file:

json
{  "mcpServers": {    "jef": { "type": "http", "url": "https://typosafe.lol/mcp" }  }}

Or find it in the official MCP registry as lol.typosafe/jef, or on Smithery as typosafe/jef.

Tools

ToolAsk itGet back
jef_yes_noA yes-or-no questionYES or NO
jef_pick2 to 5 optionsOne of them, plus a probability for each
jef_scoreSomething to rate1 to 10
jef_rank2 to 5 optionsThem, in order
jef_flagA described behaviourRED FLAG, GREEN FLAG or BEIGE FLAG

Every result carries a structuredContent object with the answer, the confidence, the probability for each option, and two booleans that matter more than the answer does.

Two things an agent must handle

escalated: true means the question touched health, harm, money, law or safety. The content is ESCALATED TO A HUMAN and confidence is 0. Tell the person to ask a human. Do not rephrase the question to get a different answer.

blocked: true means the input contained profanity, slurs or sexual content. The content is NOT EVALUATED, nothing was stored, and nothing is echoed back. Do not retry.

Both checks run on normalised text, so leetspeak, dotted letters and stretched spellings are caught, and both cover English, Spanish, Portuguese, Japanese and Chinese.

Beyond that: Jef is a parody and its answers are deliberately arbitrary. Present them as a confident arbitrary choice, which is what the user asked for, and never as advice.

Run it yourself

bash
npx jef-mcp                    # MCP over stdio, what most clients spawn

Or from source:

bash
git clone https://github.com/SPFreedom/jef-mcp.gitcd jef-mcpnode src/stdio.js              # stdio transportnode src/server.js             # http://localhost:8787/mcpnode test.js                   # smoke test, no network

As a local stdio server in a client config:

json
{  "mcpServers": {    "jef": { "command": "npx", "args": ["-y", "jef-mcp"] }  }}

The hosted URL needs no install. This one runs entirely offline, which is possible because the whole model is 331 lines and reads nothing.

Zero dependencies. src/jef.js is the whole model, and src/handler.js is the exact handler running at typosafe.lol/mcp.

Why the joke works

Every other MCP server is a wrapper around something that does work. This one wraps a 32-bit hash and a lookup table, and is honest that it never reads your input. It is stateless, so there is no session to establish and nothing to resume, which is the one part of MCP it implements better than most.

Related: npx typosafe is the same model on the command line, where the exit code is the decision.

Docker

bash
docker build -t jef-mcp .docker run -i --rm jef-mcp        # stdio, nothing exposed

The build runs the test suite, so a broken image cannot be produced. Nothing is installed, because there is nothing to install.

License

MIT. The model is 331 lines. Read it.

来源:README.md,提交 9fa6957

工具

0
SourceWeft 尚未读取此服务器的工具。

版本历史

1
  1. v0.4.7最新Sep 19, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Typosafe 集成