io.github.Rckl88/clawbackai-mcp
clawback
LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.
alive probed 2026-10-14
8tools
1.4ktokens in Claude Opus 5.5
1.6ktokens in Claude Code
0.7 %of a 200k context window
803o200k_base estimate
272 msto initialize
10 msto list tools
- Run it
- npx -y clawbackai-mcp@1.0.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- clawback 1.0.0
- Capabilities
- 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/Rckl88/clawbackai.git
- Registry
- active, updated 2026-04-12 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| optimize_llm_call | 146 | 18 % |
| set_agent_budget | 123 | 15 % |
| start_audit | 110 | 14 % |
| get_model_recommendation | 104 | 13 % |
| activate_routing | 96 | 12 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.Rckl88/clawbackai-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.