MCPLow riskUnclaimed

EvalForge Lite

Compare text LLMs across OpenRouter, Bedrock, Vertex AI and Foundry with automated grading.

thejaredchapmanthejaredchapman/evalforge-liteUpdated Oct 1, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.thejaredchapman/evalforge-lite",
  "description": "Compare text LLMs across OpenRouter, Bedrock, Vertex AI and Foundry with automated grading.",
  "title": "EvalForge Lite",
  "repository": {
    "url": "https://github.com/thejaredchapman/evalforge-lite",
    "source": "github"
  },
  "version": "1.0.1",
  "websiteUrl": "https://github.com/thejaredchapman/evalforge-lite/blob/main/docs/mcp-server.md",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "evalforge-lite",
      "version": "1.0.1",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Optional. OpenRouter API key held by the server so tool calls need no credentials for OpenRouter. If unset, pass creds in each tool call.",
          "isSecret": true,
          "name": "OPENROUTER_API_KEY"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:evalforge-lite@1.0.1
Runs install scripts—None
NetworkNoneNone
Needs credentialsOPENROUTER_API_KEYOPENROUTER_API_KEY
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #11.0.1latestOct 7, 2026