mcpcost

dev.workers.notdown-app.pulse/monitor

Pulse — heartbeat & status monitor for AI agents

Your agent pings once per run; get a public up/late/down status page. Auto-creates checks. One call.

alive probed 2026-10-05 · HTTP 200

4tools
695tokens in Claude Opus 5.5
727tokens in Claude Code
0.3 %of a 200k context window
439o200k_base estimate
276 msto initialize
199 msto list tools
Endpoint
https://pulse.notdown-app.workers.dev/mcp/{key} (streamable-http)
Host
pulse.notdown-app.workers.dev
Protocol
2025-11-25
Reports itself as
Pulse 0.1.0
Capabilities
tools
Instructions
none
Claude count
Claude Opus 5.5, measured 2026-10-05. Counted again when the tool definitions change. Method.
Website
https://pulse.notdown-app.workers.dev
Registry
active, updated 2026-08-29 · registry entry
Reachable
6 of the last 6 probes

Most expensive tools

ToolTokens (o200k)Share of this server
ping29267 %
get_check5713 %
list_checks4911 %
delete_check419 %

History

We add a row when the result changes. A server with no change keeps its last row.

ProbedResultInitToolsClaudeo200k
2026-10-05 14:02alive276 ms4695439
2026-10-05 00:25alive246 ms4439
2026-10-04 10:00alive205 ms4439
2026-10-04 07:54alive83 ms4439
2026-10-03 20:33alive215 ms4439
2026-10-03 17:50alive295 ms4439

Badge and feed

mcpcost: alive

[![mcpcost](https://mcpcost.ulehla.dev/badge/dev.workers.notdown-app.pulse/monitor.svg)](https://mcpcost.ulehla.dev/s/dev.workers.notdown-app.pulse/monitor)

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.