io.github.mrnh/rigor-mcp
rigor
Verified statistical inference for AI agents: hypothesis tests, sequential testing, power.
alive probed 2026-10-14
37tools
15ktokens in Claude Opus 5.5
15ktokens in Claude Code
7.5 %of a 200k context window
9.2ko200k_base estimate
3.1 sto initialize
21 msto list tools
- Run it
- uvx rigor-mcp==0.5.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- rigor
- Capabilities
- prompts, resources, tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/mrnh/rigor
- Registry
- active, updated 2026-09-17 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| recommend_test | 555 | 6 % |
| pairwise_group_comparisons | 522 | 6 % |
| sequential_two_sample_mean_test | 431 | 5 % |
| sequential_two_proportion_test | 389 | 4 % |
| mcnemar_test | 301 | 3 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.mrnh/rigor-mcp)
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.