com.completionkit/evals
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
AnalyticsPayments & CommerceAI & ML
updated 4d ago·validator v0.2.0·re-checked weekly
| Date | Grade | Errors | Warnings |
|---|---|---|---|
| 2026-08-24 | C | 0 | 17 |
| 2026-08-17 | C | 0 | 17 |
| 2026-08-10 | C | 0 | 17 |
| 2026-08-03 | C | 0 | 18 |
| 2026-07-27 | C | 0 | 18 |
| 2026-07-20 | auth required | — | — |
Graded by connecting to the live server and validating every tool schema. Grades re-run on every sync. Findings and grades are never editable by the publisher.
Related servers
Kick the tires on your own server: run a check