# CompletionKit

- Registry name: `com.completionkit/evals` · version 1.0.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content, Datasets & public data, Search & data
- Authentication at last check: API key
- Declared risk: Unknown (tools not visible)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.completionkit%2Fevals
- Server page: https://mcpstation.net/s/com.completionkit--evals.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://completionkit.com/mcp`

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html