evalpair

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-11-05T05:59:03.695731Z",
      "publishedAt": "2026-11-05T05:59:03.695731Z",
      "statusChangedAt": "2026-11-05T05:59:03.695731Z"
    }
  },
  "server": {
    "name": "io.github.Srikarmk/evalpair",
    "title": "evalpair",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "version": "0.1.1",
    "packages": [
      {
        "version": "0.1.1",
        "transport": {
          "type": "stdio"
        },
        "identifier": "evalpair",
        "runtimeHint": "uvx",
        "registryType": "pypi",
        "packageArguments": [
          {
            "type": "positional",
            "value": "mcp"
          }
        ],
        "environmentVariables": [
          {
            "name": "EVALPAIR_HOME",
            "description": "Folder for the call cache, saved runs and your own suites (default ~/.evalpair)."
          },
          {
            "name": "EVALPAIR_API_KEY",
            "isSecret": true,
            "description": "Bearer token for an OpenAI-compatible server, if it needs one (OPENAI_API_KEY also works)."
          }
        ]
      }
    ],
    "repository": {
      "url": "https://github.com/Srikarmk/evalpair",
      "source": "github"
    },
    "description": "Run LLM eval suites on local or hosted models; compare runs with intervals and a noise floor."
  }
}