Agent Permissions Index MCP server
app.vercel.agent-permissions-index/agent-permissions-indexagent-permissions-index.vercel.appstreamable-httpv1.0.0Scanned
Grade Claude Code, Gemini CLI and Cursor configs for risky permissions; get public config stats.
3 tools: 1 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding, 1 high
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
1 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Agent Permissions Index MCP server can do
The Agent Permissions Index MCP server is published by agent-permissions-index.vercel.app, a domain the MCP Registry verified. It has 3 tools. It can create or change data (1 tool: grade_config), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding, 1 of them high severity (sensitive-path). Each one comes with the text it matched.
Last scanned Oct 21, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Changes things 1Claude Code: ask
grade_configGrade an AI coding agent permissions config (Claude Code .claude/settings.json, Gemini CLI .gemini/settings.json, or mcp.json).1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- High
The description refers to "mcp.json".
What this check looks forMatched text
description: "...n, Gemini CLI .gemini/settings.json, or mcp.json). Returns a letter grade, findings, a s..."
Description, as the server wrote it 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.
Only reads 2Show 2 read-only tools
get_index_statsHeadline aggregate numbers from the latest weekly snapshot of public AI agent configs on GitHub.No findings
Why it is in this group
- The name "get_index_stats" says "get": a word for reading.
Description, as the server wrote it Headline aggregate numbers from the latest weekly snapshot of public AI agent configs on GitHub.
get_leaderboardAgent tools ranked by how safely their public configs are set up, with sample sizes and method.No findings
Why it is in this group
- The name "get_leaderboard" says "get": a word for reading.
Description, as the server wrote it Agent tools ranked by how safely their public configs are set up, with sample sizes and method.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:30 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 404
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: initialize answered HTTP 404.
Posture changes
- Oct 29, 2026
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
- Highgrade_config
The description refers to "mcp.json".
What this check looks forMatched text
description: "...n, Gemini CLI .gemini/settings.json, or mcp.json). Returns a letter grade, findings, a s..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 1 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-permissions-index https://agent-permissions-index.vercel.app/mcpclaude mcp add --transport http agent-permissions-index https://agent-permissions-index.vercel.app/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__agent-permissions-index__get_index_stats",
"mcp__agent-permissions-index__get_leaderboard"
],
"ask": [
"mcp__agent-permissions-index__grade_config"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-permissions-index. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/app.vercel.agent-permissions-index/agent-permissions-index/verify?hash=b6a4e791bb5872fc1f60307690cf03df7f6e51d00a335651448447dfc0e006ea" | jq -e '.changed == false'Pinned hash b6a4e791bb58, from Oct 21, 2026, 18:43 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/app.vercel.agent-permissions-index/agent-permissions-index/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/app.vercel.agent-permissions-index/agent-permissions-index)Source: MCP Registry. Synced Oct 21, 2026, 17:45 UTC.
Agent Permissions Index MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Permissions Index MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 1 finding (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Agent Permissions Index MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Permissions Index MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Agent Permissions Index MCP server have?
- 3 tools: 1 write, 2 read. grade_config, get_index_stats and get_leaderboard.
Does the Agent Permissions Index MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Agent Permissions Index MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Permissions Index MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 21, 2026.