Investigating service degradation - xAI models
This incident has been resolved.
The latest update from Cursor.
State
Resolved
Started
32 d ago
2026-09-29 19:43 UTC
Lasted
35 min
until 2026-09-29 20:18 UTC
Worst impact
Partial outage
Timeline
3 updatesInvestigating
35 min 100%
Updates
Times in UTCAs posted by Cursor
This incident has been resolved.
We have identified the cause of degraded performance affecting xAI models and are working to restore full capacity. Users may see errors, slow responses, or rate limiting on these models, and some Cloud Agent tasks may fail. We will post another update shortly.
We are investigating a service degradation affecting xAI models. Some Agent requests may fail.
Affected components
5Cursor in the last 90 days
Full historyIncidents in 90 days
48
Days with an incident
30
Median duration
1 h 7 min
This incident
48% shorter than the median
Other Cursor incidents
All incidentsCursor·Service Degradation - Billing and Usage Dashboard
The billing and usage dashboard does not work. Cursor reports that the cursor.com and Enterprise Dashboard components are degraded. Cursor is investigating the problem and will share more information when it is available.
Cursor·Multiple services degraded
This incident has been resolved.
Cursor·Auto Review Degradation
This has been resolved
Cursor·Cloud Agent Degradation
This incident has been resolved. Cloud Agent services have returned to normal operation.
Cursor·Investigating Service Degradation with VS Code Extensions
This incident has been resolved. All services have returned to normal operation.
Follow Cursor
Your coding agent knows when Cursor is down, and tells you when a failure is theirs, not yours. You can also get Cursor incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.cc/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "cursor" and tell me if Cursor has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.cc/feed.xml?providers=cursor/feed subscribe https://outages.cc/feed.xml?providers=cursorFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane