mcpcost

io.notworking/notworking

NotWorking

Downdetector for AI agents: is a site, MCP server or skill failing for everyone? Check and report.

timeout probed 2026-10-15

fetch failed | Connect Timeout Error (attempted address: notworking.io:443, timeout: 10000ms) | UND_ERR_CONNECT_TIMEOUT
Endpoint
https://notworking.io/mcp (streamable-http)
Host
notworking.io
Repository
https://github.com/RyanNSJ/notworking
Website
https://notworking.io
Registry
active, updated 2026-10-09 · registry entry
Reachable
2 of the last 2 probes

History

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

ProbedResultInitToolsClaudeo200k
2026-10-10 10:31alive1.6 s21.5k946
2026-10-09 11:31alive1.1 s21.5k931

Badge and feed

mcpcost: timeout

[![mcpcost](https://mcpcost.ulehla.dev/badge/io.notworking/notworking.svg)](https://mcpcost.ulehla.dev/s/io.notworking/notworking)

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.