Notion outage on September 2, 2026: Issue reconnecting to MCPs on custom agent
Notion reported an incident affecting Notion for 4 hours 16 minutes on 2 September 2026, from 23:04 to 03:20 UTC.
Resolved
Official incident reported by Notion
- Started
- 23:04
- 2 Sep 2026 UTC
- Resolved
- 03:20
- 3 Sep 2026 UTC
- Duration
- 4h 16m
- 4 hours 16 minutes
- Impact
- -
- as rated by Notion
- Updates
- 2
- posted by Notion
Timeline
All times UTC.
Official incident from Notion
Issue reconnecting to MCPs on custom agent
-
Official
Investigating
We are seeing degraded performance when reconnecting MCP connections for custom agents. Connections that don't require re-connecting or net new connections are unaffected.
-
Official
Resolved
The issue affecting MCP reconnections on custom agents has been resolved.
"Official" rows are quoted from Notion's public status page, www.notion-status.com. Very long posts are shortened.
What our checkpoints saw
HostTracker's checkpoints, which test www.notion.so from several locations, recorded no outage of 5 minutes or longer during this incident. A provider can report a problem that affects only some features, regions or accounts, which a check of the main address does not see. The live Notion status shows what our checks see right now.
Does your product depend on Notion?
An outage like this one reaches your users through your product, and most teams hear about it from a customer rather than from a dashboard. HostTracker watches any endpoint you name - your own site, an API you call, a vendor you resell - from 300+ locations, confirms a failure from several of them before it says anything, and then tells you by email, SMS, voice call or your chat tool.
You get the same record you are reading here for your own services: every outage timestamped, with the checks that observed it.
Independent measurement by HostTracker. Not affiliated with Notion. Official updates are quoted from Notion's public status page and remain Notion's own words.