Claude Usage runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 8 Oct 2026.
Measures whether your Claude subscription is paying off, from local logs. No upload.
What the code does
We read the source, 4 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
raw = subprocess.run(
mod = __import__("claudeusage." + SUB[cmd][0], fromlist=["main"])
dirs = {k: os.path.join(work, k) for k in ("before", "after", "control")}
env = dict(os.environ, PYTHONPATH=SRC, CLAUDEUSAGE_DATA=data_dir, CLAUDEUSAGE_LANG="ko")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Claude Usage
same job, measured the same wayClaude Code token usage, cost, and plan limits from local logs and Anthropic's usage API.
Log meals and read your nutrition diary from Claude or ChatGPT.
Start, stop and read logs of your local dev servers from Claude Code, Cursor and Codex.
Deploy local apps, add managed Postgres, and inspect logs from your AI coding agent.
Local-first MCP server: read LAS well logs and DLIS files from your own disk.
Log meals, weight and workouts in Hearth and review your progress. Subscription required.
Measures the cost, tokens and duration of a completed agent workflow from its session log.
OpenAI Codex usage from your local logs: tokens, API-equivalent cost and plan limits.
Claude Usage — questions
Answers built from our own checks of this server.