io.github.metrxbots/mcp-server
metrx-mcp-server
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.
alive probed 2026-10-14
23tools
7.7ktokens in Claude Opus 5.5
7.9ktokens in Claude Code
3.8 %of a 200k context window
4.2ko200k_base estimate
348 msto initialize
19 msto list tools
- Run it
- npx -y @metrxbot/mcp-server@0.2.2 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- metrx-mcp-server 0.2.2
- Capabilities
- prompts, 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/metrxbots/mcp-server
- Registry
- active, updated 2026-03-12 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| metrx_create_model_experiment | 358 | 8 % |
| metrx_run_cost_leak_scan | 274 | 6 % |
| metrx_set_budget | 272 | 6 % |
| metrx_configure_alert_threshold | 254 | 6 % |
| metrx_attribute_task | 233 | 6 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.metrxbots/mcp-server)
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.