Back to Browse

Evalsmith MCP Server

Developer ToolsLow Risk10.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

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

About

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

Security Report

10.0
Low Risk10.0Low Risk

Valid MCP server (2 strong, 3 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.

11 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

OpenAI-compatible endpoint for the optional LLM judge (default: Ollama on localhost)Optional

Environment variable: EVALSMITH_JUDGE_BASE_URL

Model used by the optional LLM judgeOptional

Environment variable: EVALSMITH_JUDGE_MODEL

API key for the judge endpoint, if it needs oneRequired

Environment variable: EVALSMITH_JUDGE_API_KEY

pino log level; logs go to stderrOptional

Environment variable: LOG_LEVEL

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "io-github-diegoperezg7-evalsmith-mcp": {
      "env": {
        "LOG_LEVEL": "your-log-level-here",
        "EVALSMITH_JUDGE_MODEL": "your-evalsmith-judge-model-here",
        "EVALSMITH_JUDGE_API_KEY": "your-evalsmith-judge-api-key-here",
        "EVALSMITH_JUDGE_BASE_URL": "your-evalsmith-judge-base-url-here"
      },
      "args": [
        "-y",
        "evalsmith-mcp"
      ],
      "command": "npx"
    }
  }
}

Reviews

No reviews yet

Be the first to review this server!