TypeSafe MCP

    1

    用 TypeSafe Jev 做结构化判断:分类、评分、是非概率,以及工单分流和内容审核。

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    TypeSafe MCP

    Example session with this skill installed

    把这条工单分类:标题「支付接口超时」,内容「结账页一直转圈,用户无法付款」。

    • Read your context and instructions
    • Compiled the typesafe mcp

    返回 type、priority、department、emotion、impact 的结构化答案和 token 用量。例如 priority 为 P1,department 为 backend。

    Connects securely to your tools. The creator never sees your data.

    About this skill

    把 typesafe-mcp 接到 MCP 客户端,让代理通过 stdio 调用 TypeSafe System One(Jev)。

    包含三个工具:

    • typesafe_classify:对文本、JSON 对象或数组做 choice、score、noul 判断
    • typesafe_ticket_classify:判断工单类型、优先级、负责团队、情绪和影响范围
    • typesafe_content_moderate:检测暴力、色情、仇恨言论和垃圾信息,并给出风险与处理建议

    服务使用官方 typesafe-sdk,认证失败、限流和连接错误会变成可读的 MCP 工具错误,API 密钥不会写进错误信息。

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    只提供 stdio 传输。必须有 TypeSafe API Key。内容审核只覆盖暴力、色情、仇恨言论和垃圾信息。模型只接受 jev-latest、jev-preview 或 jev-x.y.z。

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    • Free with an Agensi account

    Accounts
    GitHubTypeSafe API key
    Software
    Python 3.10+uv 或 pip
    Optional
    Git

    Permissions

    Allowed Hosts

    api.typesafe.ai
    github.com

    File Scopes

    本机
    typesafe-mcp
    目录
    MCP
    客户端配置

    TYPESAFE_API_KEY 只放在 MCP 进程环境变量里,不要写进聊天或仓库。

    Listed2 days ago

    What's inside

    Frequently Asked Questions

    需要。在 https://console.typesafe.ai/keys 创建 API Key,并放到 MCP 进程的 TYPESAFE_API_KEY。

    score 按 criteria 的零基索引计算。四个等级对应 0 到 3,不是自定义的 min/max 区间。

    不会。仓库里的 pytest 不访问 TypeSafe。

    New in LLM Ops

    Free