io.github.usekaval/kaval
Kaval
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
alive probed 2026-10-14
37tools
15ktokens in Claude Opus 5.5
16ktokens in Claude Code
7.7 %of a 200k context window
8.6ko200k_base estimate
326 msto initialize
20 msto list tools
- Run it
- npx -y @usekaval/mcp@0.8.2 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- kaval 0.8.2
- Capabilities
- 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/usekaval/kaval-clients
- Website
- https://usekaval.com
- Registry
- active, updated 2026-09-10 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| check | 1 013 | 12 % |
| verify | 598 | 7 % |
| import_facts | 577 | 7 % |
| add_source | 563 | 7 % |
| review_contract_claim | 557 | 6 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.usekaval/kaval)
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.