Confident AI MCP

Confident AI's official MCP server, connecting AI tools to the platform behind DeepEval for evaluating, observing, and iterating on LLM quality. Agents can trigger and read evaluation runs, inspect metric scores and failing test cases, manage golden datasets, and review production traces to close the loop between eval results and code changes.

{
  "mcpServers": {
    "confident-ai": {
      "command": "npx",
      "args": [],
      "env": {
        "CONFIDENT_API_KEY": "<YOUR_CONFIDENT_API_KEY>"
      }
    }
  }
}

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "description": "Maximum number of test runs to return"
    }
  }
}

{
  "type": "object",
  "required": [
    "test_run_id"
  ],
  "properties": {
    "test_run_id": {
      "type": "string",
      "description": "Identifier of the test run"
    }
  }
}

{
  "type": "object",
  "properties": {}
}