io.github.Kungie/gut
gut
Judgment calls on small, cheap models: is this spam, which team, how urgent. YES, NO or UNSURE.
alive probed 2026-10-15
4tools
1.9ktokens in Claude Opus 5.5
1.9ktokens in Claude Code
1.0 %of a 200k context window
1.1ko200k_base estimate
3.5 sto initialize
9 msto list tools
- Run it
- uvx gutfeel-mcp==0.8.2 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- gut 0.8.2
- Capabilities
- prompts, resources, tools
- Instructions
- 885 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/Kungie/gut
- Website
- https://gutpy.dev/docs/mcp.html
- Registry
- active, updated 2026-10-13 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| each | 321 | 29 % |
| classify | 291 | 26 % |
| likely | 259 | 23 % |
| rate | 254 | 23 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.Kungie/gut)
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.