Mcp Audit

Overview

Mcp Audit is a Model Context Protocol server that delivers free context-engineering audits for AI agents. It brings your own Anthropic API key and surfaces the top three findings from each scan, helping you understand how well your agent's context is engineered. As an MCP server, it integrates directly into AI assistants and exposes audit capabilities as tools the model can call.

The server runs locally via the npm package @archonics/mcp-audit and communicates over stdio. You'll need to set the ANTHROPIC_API_KEY environment variable to authenticate. Version v0.1.4 is available now under the MIT license, with full source code at archonics/mcp-audit on GitHub.

Mcp Audit belongs in the AI & Agents category and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain this server, you can claim this listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "mcp_audit": {
      "command": "npx",
      "args": [
        "-y",
        "@archonics/mcp-audit"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<anthropic-api-key>"
      }
    }
  }
}

Requires ANTHROPIC_API_KEY