You're here from our email about this server. The data on this page is free and live. Verify that you run it (about two minutes, free) to re-run checks on demand and switch on outage alerts.
Down since 2026-10-23 20:09 UTC · last checked 21:35 UTC · 452 ms · checked every about 5 minutes
Uptime
24 hours
35.21%
7 days
30.15%
30 days
50.35%
90 days
53.70%
90 days agotoday
Handshake latency p50 2505 ms · p95 4433 ms · mean time to recover 1531 min
Incidents (90 days)
Ongoing outage · 2026-10-23 20:09 UTC · 15.6 h so far · other
Outage · 2026-10-22 09:18 UTC · 25.4 h · other
Outage · 2026-10-20 21:35 UTC · 25.4 h · other
Outage · 2026-10-19 10:49 UTC · 25.4 h · other
Outage · 2026-10-17 18:57 UTC · 25.4 h · other
Outage · 2026-10-17 07:15 UTC · 8 min · timeout
Outage · 2026-10-15 18:44 UTC · 26.1 h · other
Outage · 2026-10-13 16:23 UTC · 26.2 h · other
Outage · 2026-10-11 18:11 UTC · 26.1 h · other
Outage · 2026-10-09 18:03 UTC · 26.1 h · other
Outage · 2026-10-07 18:30 UTC · 26.1 h · other
Outage · 2026-10-05 18:09 UTC · 26.1 h · other
Outage · 2026-10-03 19:58 UTC · 26.1 h · other
Outage · 2026-10-01 17:55 UTC · 26.0 h · other
Outage · 2026-09-29 19:18 UTC · 26.0 h · other
Outage · 2026-09-29 16:17 UTC · 8 min · timeout
Outage · 2026-09-28 16:06 UTC · 12 min · connect
Outage · 2026-09-27 23:22 UTC · 44 min · other
Outage · 2026-09-26 22:11 UTC · 2.2 h · other
Outage · 2026-09-25 22:16 UTC · 2.0 h · other
Outage · 2026-09-21 19:41 UTC · 26.8 h · other
Outage · 2026-09-20 23:52 UTC · 13 min · other
Outage · 2026-09-18 19:09 UTC · 26.1 h · other
Outage · 2026-09-16 18:44 UTC · 26.2 h · other
Outage · 2026-09-14 17:41 UTC · 25.8 h · other
Outage · 2026-09-12 16:38 UTC · 25.8 h · other
Outage · 2026-09-10 15:52 UTC · 26.0 h · other
Outage · 2026-09-09 22:43 UTC · 5 min · timeout
Outage · 2026-09-08 16:31 UTC · 25.9 h · other
Outage · 2026-09-06 16:34 UTC · 26.8 h · rpc
How this is measured
Checked by Glimind's probe (initialize + tools/list, never a tool call) from one region. Uptime counts a server as up when it completes the handshake, including when it asks for credentials. An outage starts at the first failed check, so short blips between checks are not seen. Every server is measured the same way; an owner's plan never changes these numbers. Owner updates are the owner's own words and sit next to the measurements, not in place of them.