Degraded performance and errors across Cursor services
This incident has been resolved.
The latest update from xAI.
State
Resolved
Started
20 d ago
2026-10-13 00:22 UTC
Lasted
2 h 46 min
until 2026-10-13 03:07 UTC
Worst impact
Degraded
Timeline
6 updatesInvestigating
2 h 46 min 100%
Updates
Times in UTCAs posted by xAI
This incident has been resolved.
All Cursor services have recovered and are operating normally, except Cloud Agents. Some Cloud Agents may still be slow to start or fail to run, and we're actively working to restore full service. We'll share another update as soon as we have more information.
Grok Bot has recovered and is operating normally. We are continuing to monitor recovery across the IDE, Cloud Agents, and other affected services, and some users may still see intermittent errors.
We are continuing to monitor recovery. Some users may still see intermittent errors.
A fix has been implemented and services are recovering. Some users may still see intermittent errors while we monitor for full restoration.
We are investigating a widespread issue affecting Cursor. Users may see errors or failed requests across the IDE, Cloud Agents, Automations, Grok Bot, and Origin. Our team is actively working to restore service.
Affected components
9xAI in the last 90 days
Full historyIncidents in 90 days
48
Days with an incident
28
Median duration
45 min
This incident
3.6× the median
Other xAI incidents
All incidentsxAI·Service Degradation - Billing and Usage Dashboard
This incident has been resolved.
xAI·Multiple services degraded
This incident has been resolved.
xAI·Grok Degradation
This incident has been resolved. Grok.com, Grok Imagine, Grok Voice, Grok (iOS), and Grok (Android) have returned to normal performance.
xAI·Auto Review Degradation
This has been resolved
xAI·Cloud Agent Degradation
This incident has been resolved. Cloud Agent services have returned to normal operation.
Follow xAI
Your coding agent knows when xAI is down, and tells you when a failure is theirs, not yours. You can also get xAI 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 "xai" and tell me if xAI 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=xai/feed subscribe https://outages.cc/feed.xml?providers=xaiFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane