agent eval for VS Code

io.github.rudrendupaul/agent-eval

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

client:VS Code transport:stdio runtime:pypi

Install agent eval in VS Code

.vscode/mcp.json

{
  "servers": {
    "agent-eval": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agent-regress-cli"
      ]
    }
  }
}

Requires agent mode. MCP: Open User Configuration puts the same block in every workspace. VS Code docs