CompletionKit MCP server

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

Category: AI & media

● Online, checked 289 min ago · 291 ms

Source: official MCP Registry entry com.completionkit/evals · repository

Direct MCP URL and setup

CLAUDE CODE

claude mcp add --transport http com-completionkit-evals https://completionkit.com/mcp

CURSOR / VS CODE (mcp.json)

{ "mcpServers": { "com-completionkit-evals": { "url": "https://completionkit.com/mcp" } } }