# permit-mcp

> permit-mcp — qinpei-dev-permit-mcp. Use this tool when you need to control and monitor AI agents' execution of MCP tools, ensuring policy compliance and approval processes are followed. It solves problems of unchecked tool execution, providing a framework for decision-making and one-use permits. The permit-mcp tool takes in policy and approval inputs, outputting execution permits to regulate AI agent actions.

Canonical page: https://skillsregistry.net/skills/qinpei-dev-permit-mcp  
JSON: https://api.skillsregistry.net/v1/skills/qinpei-dev-permit-mcp

## Description

Stop AI agents from executing MCP tools unchecked — policy, approval, JEV decisions, and one-use execution permits.

## Trust

- **Trust score (0–1):** 0.73
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/qinpei-dev/permit-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "qinpei-dev-permit-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/qinpei-dev-permit-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/qinpei-dev-permit-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt