NestDaddy

Evalsmith Mcp

io.github.diegoperezg7/evalsmith-mcp ยท v0.1.0

Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.

Connect Runs on your machine

Terminal
claude mcp add evalsmith-mcp -e EVALSMITH_JUDGE_BASE_URL=<EVALSMITH_JUDGE_BASE_URL> -e EVALSMITH_JUDGE_MODEL=<EVALSMITH_JUDGE_MODEL> -e EVALSMITH_JUDGE_API_KEY=<EVALSMITH_JUDGE_API_KEY> -e LOG_LEVEL=<LOG_LEVEL> -- npx -y [email protected]
claude_desktop_config.json
{
  "mcpServers": {
    "evalsmith-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "EVALSMITH_JUDGE_BASE_URL": "<EVALSMITH_JUDGE_BASE_URL>",
        "EVALSMITH_JUDGE_MODEL": "<EVALSMITH_JUDGE_MODEL>",
        "EVALSMITH_JUDGE_API_KEY": "<EVALSMITH_JUDGE_API_KEY>",
        "LOG_LEVEL": "<LOG_LEVEL>"
      }
    }
  }
}
~/.cursor/mcp.json
{
  "mcpServers": {
    "evalsmith-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "EVALSMITH_JUDGE_BASE_URL": "<EVALSMITH_JUDGE_BASE_URL>",
        "EVALSMITH_JUDGE_MODEL": "<EVALSMITH_JUDGE_MODEL>",
        "EVALSMITH_JUDGE_API_KEY": "<EVALSMITH_JUDGE_API_KEY>",
        "LOG_LEVEL": "<LOG_LEVEL>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "evalsmith-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "EVALSMITH_JUDGE_BASE_URL": "<EVALSMITH_JUDGE_BASE_URL>",
        "EVALSMITH_JUDGE_MODEL": "<EVALSMITH_JUDGE_MODEL>",
        "EVALSMITH_JUDGE_API_KEY": "<EVALSMITH_JUDGE_API_KEY>",
        "LOG_LEVEL": "<LOG_LEVEL>"
      }
    }
  }
}

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools

This server runs locally, so its tools are listed by your MCP client once it starts.

Environment variables

NameDescription
EVALSMITH_JUDGE_BASE_URL
Optional
OpenAI-compatible endpoint for the optional LLM judge (default: Ollama on localhost)
EVALSMITH_JUDGE_MODEL
Optional
Model used by the optional LLM judge
EVALSMITH_JUDGE_API_KEY
Optional, secret
API key for the judge endpoint, if it needs one
LOG_LEVEL
Optional
pino log level; logs go to stderr

Details

Package[email protected] (NPM, stdio)
First published28 Oct 2026
Last updated28 Oct 2026
Registry nameio.github.diegoperezg7/evalsmith-mcp

More ai and media servers See all

Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.