Skip to main content
Menu
Anthropic

Incident

Elevated errors affecting the Microsoft 365 connector

Partial outage Lasted 1d 3h · started · Anthropic's page

DWN-caa73529c6

Level
confirmed
Worst impact
Partial outage
Anthropic says
2026-11-13 00:03 to 16:40 UTC (16h 37m)
Components
claude.ai, Claude Cowork
Down Index
52of 100

Summary

Anthropic says mail, calendar and search tools in the Microsoft 365 connector are failing for most requests, and Claude for Outlook is also affected. The provider says the cause is a Microsoft 365 service incident, the issue is identified, and service has not yet been restored.

Written by anthropic/claude-haiku-5.5 from Anthropic's own updates.

What to do

  • Check whether you use Anthropic claude.ai, Claude Cowork. Check your stack

    Drop a package.json, lockfile, Terraform or a list of domains at down.guide to see every provider you depend on.
  • Confirm your retries, queues and scheduled jobs caught up after the 1d 3h it lasted.

    Anything that failed between 2026-11-12 17:52 UTC and 2026-11-13 21:49 UTC may need a replay.
  • Subscribe to Anthropic's feed to hear about the next one first. RSS feed

    https://down.guide/feed?provider=anthropic works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Root cause

This issue is caused by a Microsoft 365 service incident, and mail, calendar and search tools in the Microsoft 365 connector are still failing for most requests.
Read the postmortem

Updates from Anthropic 7

  1. investigating

    We are investigating elevated errors and slow responses affecting the Microsoft 365 connector. Requests to mail, SharePoint, Teams chat and calendar through the connector may fail, and new connections to the connector may not complete. We will provide an update as soon as possible.

    provider

  2. identified

    We have identified an issue with an upstream provider affecting the Microsoft 365 connector. Mail, calendar and search tools are failing for most requests, and new connections to the connector may not complete. We are in contact with them and will provide an update as soon as possible.

    provider

  3. identified

    We are continuing to work with our upstream provider on this issue. Mail, calendar and search tools in the Microsoft 365 connector are still failing for most requests. Claude for Outlook is also affected: mail and calendar actions may fail, and some users may not be able to open the add-in. We will provide another update within the hour.

    provider

  4. identified

    We are continuing to work with our upstream provider, who is restarting affected servers. Mail, calendar and search tools in the Microsoft 365 connector are still failing for most requests, and Claude for Outlook remains affected. We will provide another update as soon as we have more information.

    provider

  5. identified

    This issue is caused by a Microsoft 365 service incident, and mail, calendar and search tools in the Microsoft 365 connector are still failing for most requests. Claude for Outlook remains affected. You can follow Microsoft's progress at https://status.cloud.microsoft. We will update this post when service is restored.

    provider

  6. monitoring

    We're seeing signs of recovery for the Microsoft 365 connector. Claude for Outlook is also recovering. Some SharePoint search requests are still returning errors. Microsoft's incident remains open, so errors may return. We're continuing to monitor and will update this post as soon as we have more info.

    provider

  7. resolved

    This incident has been resolved. From 08:03 PT / 16:03 UTC on November 12 to 08:40 PT / 16:40 UTC on November 13, mail, calendar and search tools in the Microsoft 365 connector and Claude for Outlook returned errors for many requests because of a Microsoft 365 service incident. Microsoft is still completing its recovery, so you may see occasional errors or delays.

    provider

Reports count in aggregate; nothing about you is shown.

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.

Questions about DWN-caa73529c6

Is Anthropic still down?

No, this incident was resolved 2026-11-13 21:49 UTC. For Anthropic's live state, see https://down.guide/providers/anthropic.

How long did it last?

1d 3h, from 2026-11-12 17:52 UTC to 2026-11-13 21:49 UTC, by the times Anthropic posted.

What was affected?

Anthropic named claude.ai, Claude Cowork.

What caused it?

Anthropic wrote: "This issue is caused by a Microsoft 365 service incident, and mail, calendar and search tools in the Microsoft 365 connector are still failing for most requests." The postmortem: https://stspg.io/m0rbx38nmy1c

Where does this come from?

Anthropic's official status page, https://status.claude.com, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.