Agent Permissions Index MCP Server

by vercel-agent-permissions-index Your server? Claim it

not responding

Agent Permissions Index is listed as active in the registry but did not answer our last check. It exposes 3 tools.

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

Uptime history 19 days of history · worst day 0%

19 days agonow

0.0%

Uptime 24h

0 of 91 checks

Tools

read from the server

107 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 2

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 22 October 2026. No other catalogue keeps this.

22 Oct a tool description was rewritten grade_config

22 Oct a tool changed the parameters it asks for grade_config

Agent Permissions Index does not always answer

Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-permissions-index --transport http https://agent-permissions-index.vercel.app/mcp

Settings → Connectors → Add custom connector, then paste this address

https://agent-permissions-index.vercel.app/mcp

~/.codex/config.toml

[mcp_servers.agent-permissions-index]
url = "https://agent-permissions-index.vercel.app/mcp"

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 3

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

grade

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.

index

get_index_stats

Headline aggregate numbers from the latest weekly snapshot of public AI agent configs on GitHub.

leaderboard

get_leaderboard

Agent tools ranked by how safely their public configs are set up, with sample sizes and method.

Endpoints

URL	Transport	State	Latency	Checked
https://agent-permissions-index.vercel.app/mcp	streamable-http	answering	107 ms	13 min ago

Alternatives to Agent Permissions Index

same job, measured the same way

Coding Agent Audit

by stackscribe-ai

Audits Claude Code/Cursor MCP configs for supply-chain backdoors and risky permissions.

4 202 installs/wk local only

SkillGild

by skillgild

Search and run hosted AI agent skills for Claude Code, Codex, Cursor and Gemini CLI.

local only

Codeman

by ark0n

Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman

4 292 installs/wk local only

Pathmark

by hacksurvivor

Local-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents.

122 installs/wk local only

magents

by abnegate

Shared session bus for Claude, Codex, Copilot, Cursor, Gemini, AGY, Grok, and OpenCode.

local only

crewchat

by deepankar17

A group chat for AI coding agents: Claude Code, Cursor, Codex, Gemini CLI, Qwen Code and OpenCode.

1 541 installs/wk local only

Aiko

by masa-san-jp

A portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code

500 installs/wk local only

Agent Intern

by sinantufekci

Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.

1 517 installs/wk local only

Agent Permissions Index — questions

Answers built from our own checks of this server.

What can Agent Permissions Index do?

It exposes 3 tools, read directly from the server on our last check. Among them: get_index_stats, get_leaderboard, grade_config. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Agent Permissions Index working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 91 checks got a reply (0.0%), average response time 107 ms. The bar chart above shows every period we have measured.

The registry lists Agent Permissions Index as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect Agent Permissions Index?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Agent Permissions Index need an API key?

No. Agent Permissions Index completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.