跳过安装。2 分钟内即可运行。
在 cloud.anythingmcp.com 开始免费试用，一键添加 Jev by TypeSafe，然后将你的 AI 客户端（Claude、ChatGPT、Copilot 或 Cursor）指向生成的 MCP 端点。无需 Docker，无需 git clone，无需任何工程经验。
摘要
借助 TypeSafe 的 System One 模型 Jev，为 AI 智能体提供快速、低成本的是/否、分类和评分决策：约 300 毫秒返回带校准概率的类型化答案，而不是一段需要解析的文字。
试试这样问
Jev by TypeSafe 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Jev by TypeSafe、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Jev by TypeSafe + Gemini
借助 TypeSafe 的 System One 模型 Jev，为 AI 智能体提供快速、低成本的是/否、分类和评分决策：约 300 毫秒返回带校准概率的类型化答案，而不是一段需要解析的文字。
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
TYPESAFE_API_KEY
步骤 1 — 获取凭证
Jev is a decision model, not a chat model. You give it state (the evidence) and one or more typed questions; it returns a number or an option with probabilities in about 300 ms. It never writes text. Use it when an agent needs a judgment it can branch on: is this urgent, which team owns it, how risky is it, does this reply answer the question, is this record a duplicate.
Start with jev_playbook. It costs no API call and explains how to phrase questions, what to put in state and how to read the probabilities.
Setup: create an API key at https://console.typesafe.ai and paste it into TYPESAFE_API_KEY. Jev is billed per input token (about $0.04 per million), output is free.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Jev by TypeSafe应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
jev_playbook | START HERE: returns, with NO API call, how to use Jev well: which question type to pick, how to structure state, how to write the question… |
jev_yes_no | Ask Jev ONE yes/no question about some evidence |
jev_classify | Ask Jev to pick ONE option from a set you define (routing, labelling, intent, triage) |
jev_rate | Ask Jev to place the evidence on an ordered scale you define (severity, lead fit, quality, sentiment) |
jev_ask | Full Jev API: ask SEVERAL typed questions about the same state in one call (answered in parallel, state billed once) |
jev_list_models | List the Jev model names your API key can use in the model field (aliases such as jev-latest and jev-preview, with release dates) |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?
