# Agent Permissions Index (remote · agent-permissions-index.vercel.app)

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

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `agent-permissions-index.vercel.app`: 66/100 (this document), [markdown](https://verifymcp.io/servers/app-vercel-agent-permissions-index-agent-permissions-index/agent-permissions-index.md), [page](https://verifymcp.io/servers/app-vercel-agent-permissions-index-agent-permissions-index/agent-permissions-index)

## Channel facts

- Endpoint: `https://agent-permissions-index.vercel.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-22.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 3 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 147 tokens (~49/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Agent Permissions Index MCP server?

Agent Permissions Index is a hosted endpoint at https://agent-permissions-index.vercel.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http app-vercel-agent-permissions-index-agent-permiss 'https://agent-permissions-index.vercel.app/mcp'
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-vercel-agent-permissions-index-agent-permiss": {
      "type": "remote",
      "url": "https://agent-permissions-index.vercel.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-vercel-agent-permissions-index-agent-permiss --url 'https://agent-permissions-index.vercel.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-vercel-agent-permissions-index-agent-permiss:
    url: "https://agent-permissions-index.vercel.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-vercel-agent-permissions-index-agent-permiss": {
      "Transport": "http",
      "Url": "https://agent-permissions-index.vercel.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-vercel-agent-permissions-index-agent-permiss -t streamable-http -u 'https://agent-permissions-index.vercel.app/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 66, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-21 (score 65)

First indexed and scored.

## MCP tools (3)

### `grade_config` (~91 tokens)

Grade agent config

Grade an AI coding agent permissions config (Claude Code .claude/settings.json, Gemini CLI .gemini/settings.json, or mcp.json). Returns a letter grade, findings, a safer config and README badge Markdown. Inputs are not stored or logged.

Input parameters:

- `config` (string, required): The config file contents as JSON text (max 100 KB)
- `tool` (string): Which tool the config is for

### `get_index_stats` (~27 tokens)

Agent Permissions Index stats

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

### `get_leaderboard` (~29 tokens)

Agent safety leaderboard

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

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-vercel-agent-permissions-index-agent-permissions-index/agent-permissions-index#diagnostics

## Score history

- 2026-10-22: 66
- 2026-10-21: 65

## Common questions

### What is the Agent Permissions Index MCP server?

Agent Permissions Index is an MCP server listed in the public MCP registry as app.vercel.agent-permissions-index/agent-permissions-index. Grade Claude Code, Gemini CLI and Cursor configs for risky permissions; get public config stats. This page covers its hosted endpoint (https://agent-permissions-index.vercel.app/mcp).

### Is the Agent Permissions Index MCP server safe to use?

Agent Permissions Index scores 66 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Permissions Index MCP server expose?

Agent Permissions Index exposes 3 tools: grade_config, get_index_stats, get_leaderboard. Their descriptions and schemas cost roughly 147 tokens of context every time the server is loaded.

### Does the Agent Permissions Index MCP server require authentication?

No. We connected to Agent Permissions Index without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Permissions Index MCP server still maintained?

Agent Permissions Index is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agent-permissions-index.vercel.app/mcp
- Website: https://agent-permissions-index.vercel.app/mcp-docs
- Changelog RSS feed: https://verifymcp.io/servers/app-vercel-agent-permissions-index-agent-permissions-index/agent-permissions-index.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-vercel-agent-permissions-index-agent-permissions-index/agent-permissions-index.json
- HTML version of this page: https://verifymcp.io/servers/app-vercel-agent-permissions-index-agent-permissions-index/agent-permissions-index