TypeSafe MCP
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
Works with the AI Agents you already use
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。
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
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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
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 forever
No account required to browse
Trust & safety
Security scan
Security scan passed 2 days ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts
File Scopes
TYPESAFE_API_KEY 只放在 MCP 进程环境变量里,不要写进聊天或仓库。