io.github.bikemeardsley/where-my-hug
where-my-hug
Which parts of an ML need Hugging Face already covers. Every model and dataset checked live.
alive probed 2026-10-15
3tools
1.9ktokens in Claude Opus 5.5
1.9ktokens in Claude Code
0.9 %of a 200k context window
1.2ko200k_base estimate
442 msto initialize
13 msto list tools
- Run it
- npx -y where-my-hug@0.2.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- where-my-hug 0.2.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/bikemeardsley/where-my-hug
- Registry
- active, updated 2026-10-14 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| where_my_hug_verify | 547 | 47 % |
| where_my_hug | 321 | 28 % |
| where_my_hug_search | 293 | 25 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.bikemeardsley/where-my-hug)
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.