Skip to main content
Granola

Claude unable to connect to Granola MCP

Partial outage Lasted 1d · started · Granola's page

Level
confirmed
Worst impact
Partial outage
Regions
us
Down Index
37of 100

What to do

  • Check whether you use Granola in us. Check your stack

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

    Anything that failed between 2026-03-09 15:50 UTC and 2026-03-10 15:55 UTC may need a replay.
  • Subscribe to Granola's feed to hear about the next one first. RSS feed

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

Updates from Granola 4

  1. investigating

    We're investigating reports that users on [claude.ai](http://claude.ai "claude.ai") are unable to connect to Granola MCP. We're currently working on a mitigation for this. Other AI/LLM apps (including Claude Code/Cowork) are able to connect to MCP as far as we're aware currently.

    provider

  2. identified

    We've identified a possible cause of this and are currently testing a fix. We've also been informed this is affected all Claude products ([claude.ai](http://claude.ai "claude.ai"), Claude Code and Claude Cowork).

    provider

  3. monitoring

    We've put a fix in place to mitigate the issues seen with Claude connecting to the Granola MCP yesterday - it looks like we're back up and running again based on our metrics. If you're still having issues with the Granola MCP in Claude, please try disconnecting and reconnecting from the MCP. You can do this at [claude.ai/customize/connectors](http://claude.ai/customize/connectors "claude.ai/customize/connectors") - click on Granola, then the three dots in the top-right corner and choose Disconnect. Without refreshing the page, choose Connect again. If you're still having issues, please email us at [hey@granola.so](mailto:hey@granola.so "hey@granola.so").

    provider

  4. resolved

    Apologies for the disruption to MCP with Claude, we've worked through these with the Claude team and it looks like we're back up and running. If you're having issues, please follow the troubleshooting steps here: [https://docs.granola.ai/help-center/sharing/integrations/mcp#granola-mcp](https://docs.granola.ai/help-center/sharing/integrations/mcp#granola-mcp "https://docs.granola.ai/help-center/sharing/integrations/mcp#granola-mcp")

    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-95c3bef202

Is Granola still down?

No, this incident was resolved 2026-03-10 15:55 UTC. For Granola's live state, see https://down.guide/granola.

How long did it last?

1d, from 2026-03-09 15:50 UTC to 2026-03-10 15:55 UTC, by the times Granola posted.

What was affected?

Granola named in us.

What caused it?

Granola hasn't published a root cause. If it does, it shows here.

Where does this come from?

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