Persistent Crashes and Timeouts!

Hey, based on the screenshot it looks like a Provider Error. This was a widespread issue on February 19, and several users reported the same thing.

A couple things to try:

  1. Cursor Settings > Tools & MCP: if you have any MCP servers connected, temporarily disable them all. This fixed it for most users with this error.
  2. Cursor Settings > Models: make sure “Override OpenAI Base URL” is turned off, and remove any third-party API keys if you added them.
  3. Network settings: go to Settings > Network and try enabling “Http Compatibility Mode” (disables HTTP/2). This helped another user: thread (Again We're having trouble connecting to the model provider. This might be temporary - please try again in a moment).
  4. Try switching to a different model for now. Some models were impacted more than others.

Which model were you using when this happened? And do you have any MCP servers set up?