← Back to Plugins
MCP Server MCP

CompletionKit

github By github 👁 1 views ▲ 0 votes

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

Configuration Example

{
  "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"
        }
      ]
    }
  ],
  "packages": []
}
mcp model-context-protocol streamable-http

Comments

Sign in to leave a comment

Loading comments...