io.github.rccola990-cloud/mcp-token-optimizer
mcp-token-optimizer
Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
alive probed 2026-10-15
4tools
851tokens in Claude Opus 5.5
911tokens in Claude Code
0.4 %of a 200k context window
494o200k_base estimate
423 msto initialize
4 msto list tools
- Run it
- npx -y mcp-token-optimizer@0.1.1 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- mcp-token-optimizer 0.1.0
- 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/rccola990-cloud/mcp-token-optimizer
- Registry
- active, updated 2026-06-18 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| estimate_cost | 133 | 27 % |
| slim_prompt | 131 | 27 % |
| compare_model_costs | 117 | 24 % |
| count_tokens | 113 | 23 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.rccola990-cloud/mcp-token-optimizer)
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.