
TypoSafe AI — Jef
lol.typosafe由 typosafe.lol 發布官方發布者v0.4.7更新於 Oct 24, 2026
Jef decides. Give it options, it returns one with a confidence, never a sentence. A parody.
概覽
一個惡搞性質的決策伺服器,不生成文字,而是回傳任意的是/否、選項、評分、排序或標記,並附上信心度。
- 可以做什麼
- 提出一個是非題,取得 YES 或 NO,並附上信心度與結構化內容,其中包含升級與封鎖標記,助理應依此處理,而不是換個問法重試。
- 適用情境
- 當你想要一個刻意任意但可重現的決定——在幾個選項中挑一個、給 1 到 10 分、排序,或給出紅旗/綠旗/米色旗——而且清楚這只是玩笑、不是建議時使用。
- 執行需求
- 可使用託管的遠端端點,不需安裝、金鑰或帳號;也可在本機執行 npm 套件 jef-mcp(stdio),需要 Node.js 與 npx,本機版本完全離線且沒有相依套件。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 TypoSafe AI — Jef,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
交給代理程式安裝
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/lol.typosafe%2Fjef/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。其他 MCP 客戶端
把它新增到你客戶端的 mcpServers 設定中。
{
"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.
Claude Code:
Anything that reads a config file:
Or find it in the official MCP registry
as lol.typosafe/jef, or on Smithery as typosafe/jef.
Tools
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
Or from source:
As a local stdio server in a client config:
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
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.
來源:README.md,提交 9fa6957
工具
0版本歷史
1- v0.4.7最新Sep 19, 2026
評分
已滿足適用檢查項的 85%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通必需25 分
- 已宣告認證方式必需10 分
- 已列出工具必需15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分