agent eval for Windsurf

io.github.rudrendupaul/agent-eval

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

client:Windsurf transport:stdio runtime:pypi

Install agent eval in Windsurf

~/.codeium/windsurf/mcp_config.json · windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

{
  "mcpServers": {
    "agent-eval": {
      "command": "uvx",
      "args": [
        "agent-regress-cli"
      ]
    }
  }
}

Global only — Windsurf has no per-project MCP config. Refresh Cascade after saving. Windsurf docs