MCP server (for agents)
Published as io.github.sriinnu/tokmeter in the MCP registry, shipped in
@sriinnu/tokmeter-mcp. The entry point is the serve subcommand:
{ "command": "npx", "args": ["-y", "@sriinnu/tokmeter-mcp", "serve"] }Claude Code: claude mcp add tokmeter --scope user -- npx -y @sriinnu/tokmeter-mcp serve.
All tools are prefixed tokmeter_. Start with tokmeter_pulse — it answers most
“what am I spending” questions in one call. Full list grouped by purpose:
MCP tool reference.
Cleanup is gated server-side. tokmeter_cleanup_execute refuses to run
unless passed confirm: "DELETE" and writes a backup first by default; always
call tokmeter_cleanup_preview first. The human “are you sure?” over MCP comes
from your client’s tool-approval UI, not from inside the server. See
Backup & restore.
Daemon HTTP
tokmeter-mcp daemon start runs a warm core so repeated reads never re-scan the
corpus. Read-only JSON on 127.0.0.1:9877 (WebSocket 9876 is for live session
registration, not queries):
| Endpoint | Returns |
|---|---|
/api/ready |
Whether the warm core finished loading |
/api/quick |
Lifetime totals + live signals — cheapest poll |
/api/today |
Today’s totals and per-project split |
/api/summary |
The full TokmeterSummary |
/api/stats, /api/daily, /api/models, /api/providers, /api/projects, /api/sessions |
Scoped aggregates |
/api/statbar-signals |
Burn rate, cache hit, pace, billing window |
/api/rates |
Per-model $/M rates (input, output, cache read/write) with the price source; ?scope=all for every model with usage |
Never run a full scan in a loop. A full corpus scan is memory-heavy; anything polling more than once a minute should read the daemon or the MCP server, which hold warm state.
Something wrong or out of date? This page is generated from its source on GitHub.