← Index

io.github.archonics/mcp-audit

io.github.archonics/mcp-audit·v0.1.4·AI & LLMs
Quality Score
80
/100

Free context-engineering audits for AI agents. BYOK Anthropic key. Top-3 findings per scan.

§01  Install
Claude Desktop (claude_desktop_config.json)
{
  "mcpServers": {
    "mcp-audit": {
      "command": "npx",
      "args": [
        "-y",
        "@archonics/mcp-audit"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>"
      }
    }
  }
}
Cursor (.cursor/mcp.json)
{
  "mcpServers": {
    "mcp-audit": {
      "command": "npx",
      "args": [
        "-y",
        "@archonics/mcp-audit"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>"
      }
    }
  }
}
Cline (cline_mcp_settings.json)
npx -y @archonics/mcp-audit
§02  Environment variables
ANTHROPIC_API_KEY
requiredsecret

Your Anthropic API key. Required — the audit engine calls Claude directly from your machine.

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
5
§04  Alternatives in AI & LLMs