ToolVet
83trust / 100

Agent Permissions Index

by agent-permissions-index.vercel.app in AI models & inference

MCP serverPassing, checked 12 h ago

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

https://agent-permissions-index.vercel.app/mcp
Tools
3
open to any client
Uptime
100%
last 30 days
Response time
251 ms
486 ms slowest 5%
Last check
Passed
12 h ago, next any minute now

Scan it nowHow to connect

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to connect

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "agent-permissions-index": {
      "type": "http",
      "url": "https://agent-permissions-index.vercel.app/mcp"
    }
  }
}

3 tools

  • 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.

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
12 h agoPassed200251 ms
26 h agoPassed200206 ms
39 h agoPassed200225 ms
2 days agoPassed200294 ms
3 days agoPassed200273 ms
Show 10 older checks
3 days agoPassed200215 ms
4 days agoPassed200193 ms
4 days agoPassed200260 ms
5 days agoPassed200257 ms
5 days agoPassed200222 ms
5 days agoPassed200252 ms
6 days agoPassed200256 ms
6 days agoPassed200219 ms
7 days agoPassed200322 ms
7 days agoPassed200251 ms