agents-permissions

Cross-agent permission policy specification for AI coding agents

Install Command

npx -y agents-permissions

Claude Desktop Config

{
  "mcpServers": {
    "agents-permissions": {
      "command": "npx",
      "args": [
        "-y",
        "agents-permissions"
      ]
    }
  }
}

agents-permissions is a community MCP server that connects AI assistants like Claude to cross-agent permission policy specification for ai coding agents. It runs locally on your machine, keeping your data private and giving you full control over the connection. Security teams can leverage it to run checks and gather intelligence through natural-language prompts.

About agents-permissions

Overview

Cross-agent permission policy specification for AI coding agents

Topics

agents, permissions, ai, coding-agent, claude-code, codex, opencode, crush, cross-agent, mcp, mcp-server, policy, sync, zod

Who Should Use agents-permissions?

1Run security scans and vulnerability checks from your AI assistant
2Automate compliance checks and audit log reviews
3Integrate threat intelligence feeds into your AI workflow
4Let Claude assist with penetration testing and security research tasks

How to Install agents-permissions

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.