com.rubrkit/rubrkit
rubrkit
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
alive probed 2026-10-05 · HTTP 200
41tools
8.1ktokens in Claude Opus 5.5
8.5ktokens in Claude Code
4.0 %of a 200k context window
4.3ko200k_base estimate
503 msto initialize
383 msto list tools
- Endpoint
- https://www.rubrkit.com/api/v1/mcp (streamable-http)
- Host
- www.rubrkit.com
- Protocol
- 2025-06-18
- Reports itself as
- rubrkit 0.1.0
- Capabilities
- prompts, resources, tools
- Instructions
- 162 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-05. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/liberat0r/react-rubrkit
- Website
- https://www.rubrkit.com
- Registry
- active, updated 2026-06-29 · registry entry
- Reachable
- 6 of the last 6 probes
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| rubrkit_run_evals | 280 | 7 % |
| rubrkit_start_audit | 210 | 5 % |
| rubrkit_export_proof_report | 189 | 4 % |
| rubrkit_compact_artifact_file | 178 | 4 % |
| rubrkit_add_golden_case | 165 | 4 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-05 13:38 | alive | 503 ms | 41 | 8.1k | 4.3k |
| 2026-10-05 00:20 | alive | 317 ms | 41 | 4.3k | |
| 2026-10-04 09:58 | alive | 1.0 s | 41 | 4.3k | |
| 2026-10-04 07:51 | alive | 538 ms | 41 | 4.3k | |
| 2026-10-03 20:31 | alive | 627 ms | 41 | 4.3k | |
| 2026-10-03 17:49 | alive | 829 ms | 41 | 4.3k |
Badge and feed
[](https://mcpcost.ulehla.dev/s/com.rubrkit/rubrkit)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.