@vasikmansuri/agentconfig-doctor

MCP security scanner and config linter for AI coding agents: finds exposed secrets, risky commands, broad permissions and invalid MCP servers in Claude Code, Cursor and VS Code (Copilot) configs. Local-first, no telemetry.

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "npm-vasikmansuri-agentconfig-doctor": {
      "command": "npx",
      "args": [
        "@vasikmansuri/agentconfig-doctor"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://www.npmjs.com/package/@vasikmansuri/agentconfig-doctor

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "npm-vasikmansuri-agentconfig-doctor": {
      "command": "npx",
      "args": [
        "@vasikmansuri/agentconfig-doctor"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

GitHub

Related servers