CompletionKit
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Description supplied by the publisher; it is a claim, not verified evidence.
- Name
- com.completionkit/evals
- Listed in
- Official MCP Registry
- Publisher
- Homemade Software (verified publisher)
- Latest version
- 1.0.0
- Published
- 2026-07-18
- License
- NOASSERTION
- Evidence
- Analyzed by UND Assay
Source: https://github.com/homemade-software-inc/completion-kit