MCP servers disconnect every two hours
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.5k
- PR merge metrics
- PR metrics pending
Description
What version of the Codex App are you using (From “About Codex” dialog)?
Version 26.810.52044
What subscription do you have?
Pro
What platform is your computer?
Microsoft Windows NT 10.0.26200.0 x64
What issue are you seeing?
I have multiple MCP servers connected and most of them work fine. But two days ago, two of my MCP servers (Miro and OpenBrain) started prompting me for reconnection about every two hours. I reconnect them successfully and then two hours later, they both need reconnecting again. I had Codex CLI examine them and Codex said they looked healthy.
What steps can reproduce the bug?
Feedback ID: no-active-thread-01a01503-e740-7343-86f7-dc2ea5ec21ab
What is the expected behavior?
I'm not sure these MCP servers ever needed reconnecting before two days ago. My expectation is that they shouldn't need to be reconnected more often than once/month.
Additional information
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the reported Feedback ID no-active-thread-01a01503-e740-7343-86f7-dc2ea5ec21ab and the MCP connection handling in the Codex CLI. Reproduce on Windows with the Miro and OpenBrain servers, then trace why both require reconnection every two hours; done means they remain connected for the expected interval.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- networking
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100