The Ultimate Critic
Server Details
Check AI work against requirements and return structured verdicts, findings, and repair steps.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool targets a unique operation: evaluation, preview, pricing, and usage tracking. No overlap or ambiguity.
All tools share the 'tuc.' prefix and follow a verb-like naming pattern (evaluate, preview, quote, usage). Consistent and predictable.
Four tools cover the essential functions of the service (evaluate, preview, pricing, usage) without being excessive or insufficient.
The set covers core workflows, but lacks a tool to retrieve past evaluations or manage results, which could be a minor gap for advanced use.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Preflight QA for AI-agent deliverables with structured verdicts and repair guidance.
Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax.
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
Related MCP Servers
- AlicenseAqualityCmaintenanceValidates AI-generated artifacts (JSON, API responses, SQL) against a contract and returns a verdict.134 npm2MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents and CI to verify rendered web UIs against design token usage, layout constraints, and accessibility rules, returning concise pass/fail verdicts with actionable findings.12 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to call a check that flags invented specifics, copied passages, and rule breaks in drafts against an approved, versioned standard. Returns actionable tool results so agents can identify and rewrite offending spans.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to submit code, files, or diffs for deterministic checks and optional re-verified LLM repair, returning cleaned code, structured findings, and a pass/fixed/reject verdict.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.