MCPLow riskUnclaimed

CompletionKit

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

completionkit.comcompletionkit.com/evals★ 3Updated Jul 18, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "com.completionkit/evals",
  "description": "Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.",
  "title": "CompletionKit",
  "repository": {
    "url": "https://github.com/homemade-software-inc/completion-kit",
    "source": "github"
  },
  "version": "1.0.0",
  "websiteUrl": "https://completionkit.com",
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://completionkit.com/mcp",
      "headers": [
        {
          "description": "Your CompletionKit API token as: Bearer <token>. Create one under Settings > API tokens.",
          "isRequired": true,
          "isSecret": true,
          "name": "Authorization"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—None
Installs—None
Runs install scripts—None
Networkcompletionkit.comcompletionkit.com
Needs credentialsAuthorizationAuthorization
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. #11.0.0latestOct 7, 2026