CompletionKit
AI & ML
Open Access
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Overview
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Capabilities
Authentication
Type: Open Access
Provider: none
Setup Instructions:
See provider documentation for connection details.
Endpoints
| Production: | https://completionkit.com/mcp |
Maintainer
completionkit
GitHub: @
Website: completionkit.com
Tags
mcp
remote