Agent Permissions Index

app.vercel.agent-permissions-indexPublished by agent-permissions-index.vercel.appOfficial publisherv1.0.0Updated Oct 26, 2026

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

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Grades AI coding agent permission configs (Claude Code, Gemini CLI, Cursor, Codex) and reports public config safety stats and leaderboards.

What you can do
  • Grade a pasted agent permissions config for Claude Code, Gemini CLI, mcp.json or Codex CLI, returning a letter grade, findings and a safer config
  • Generate README badge Markdown from the grading result
  • Read headline aggregate numbers from the latest weekly snapshot of public AI agent configs on GitHub
  • Compare agent tools on a leaderboard ranked by how safely their public configs are set up, with sample sizes and method
When to use it
Useful when you maintain or review an AI coding agent's settings file and want a quick safety check plus a hardened version, or when you want context on how other tools' public configs are configured.
Requirements
Remote streamable HTTP endpoint; no authentication, environment variables or headers declared. Nothing to install locally.
Before you install
You submit your agent config contents to a third-party hosted service; the tool states inputs are not stored or logged, but that is the provider's claim. Review the returned safer config before adopting it, since it changes permission settings.

Installation

In SourceWeft

  1. Open Agent Permissions Index in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/app.vercel.agent-permissions-index%2Fagent-permissions-index/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

3

grade_config

Grade agent 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.

Parameterstoolconfigrequired

get_index_stats

Agent Permissions Index stats

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

Takes no parameters.

get_leaderboard

Agent safety leaderboard

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

Takes no parameters.

Version history

1
  1. v1.0.0LatestOct 20, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Vercel integrations

Vercel Mcp

Published by GitHub account mrfentmen

Query the Vercel API (token; set VERCEL_TOKEN, Bearer): projects, project details, deployments.

STDIODesktop only
Cloud & InfrastructureNot validated yetOct 25, 2026

Perceptdot Vercel

Published by GitHub account perceptdot

A local MCP server that gives an AI assistant vision into Vercel deployments, with ROI measurement, according to its provider.

STDIODesktop only
Cloud & InfrastructureNot validated yetOct 25, 2026

Vercel MCP Pro

Published by GitHub account helbertparanhos

A local MCP server that gives an assistant broad access to the Vercel REST API: deployments, projects, environment variables, domains, DNS, certificates, logs,

STDIODesktop only
Cloud & InfrastructureNot validated yetOct 24, 2026

Vercel Deployment Mcp

Published by GitHub account addiplus

A local stdio MCP server that lets an assistant read Vercel projects and deployments using a Vercel API token.

STDIODesktop only
Cloud & InfrastructureNot validated yetOct 24, 2026

Vercel

com.pulsemcp

Local MCP server for Vercel that lets an assistant list, inspect, create, promote, roll back and delete deployments and read build and runtime logs.

STDIODesktop only
Cloud & InfrastructureNot validated yetOct 24, 2026