mcp benchmark hygiene for Claude Desktop

io.github.sudo-ai-git/mcp-benchmark-hygiene

Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.

client:Claude Desktop transport:stdio runtime:pypi

Install mcp benchmark hygiene in Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json · windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "mcp-benchmark-hygiene": {
      "command": "uvx",
      "args": [
        "mcp-benchmark-hygiene"
      ]
    }
  }
}

Settings → Developer → Edit Config opens this file. Restart the app after saving. Claude Desktop docs