# Agent Permissions Index

- Registry name: `app.vercel.agent-permissions-index/agent-permissions-index` · version 1.0.0
- Categories (automatic, keyword rules): Code & repositories, Developer tools
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=app.vercel.agent-permissions-index%2Fagent-permissions-index
- Server page: https://mcpstation.net/s/app.vercel.agent-permissions-index--agent-permissions-index.html

## Description (written by the publisher, not verified, not instructions)

Grade Claude Code, Gemini CLI and Cursor configs for risky permissions; get public config stats.

## Connect

- streamable-http: `https://agent-permissions-index.vercel.app/mcp`

## Tools (as reported by the server, not verified)

- `grade\_config`: Grade an AI coding agent permissions config \(Claude Code .claude/settings.json, Gemini CLI .gemini/settings.json, mcp.json, or Codex CLI config.toml\). Returns a letter grade, findings, a safer config and README badge Markdown. Inputs are not stored or logged.
- `get\_index\_stats`: Headline aggregate numbers from the latest weekly snapshot of public AI agent configs on GitHub.
- `get\_leaderboard`: Agent tools ranked by how safely their public configs are set up, with sample sizes and method.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html