/new fails to load STDIO MCP and requires /mcp reload
Open
Nobody has claimed this yet.
triage
- Dominant language
- Shell
- Stars
- 11.2k
- Forks
- 1.9k
- Avg merge
- 14h 16m
- Merged PRs (30d)
- 6
Description
Describe the bug
I'm seeing an issue after upgrading to 1.0.8x. My custom STDIO MCP server is failing to load after a /new. It works fine when loading from Copilot CLI in a fresh session.
Affected version
GitHub Copilot CLI 1.0.83.
Steps to reproduce the behavior
- In an existing Copilot CLI session, type /new
- An error will surface:
Failed to connect to MCP server "<insert MCP name here>": MCP server "<insert MCP name here>" connection was cancelled. Execute '/mcp show <insert MCP name here>' to inspect or check the logs
- Trigger /mcp reload and it works
Expected behavior
/new should not fail to load servers due to a race.
Additional context
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 by reproducing the failure with /new in an existing Copilot CLI session, then compare it with /mcp reload and inspect the reported logs. Trace the STDIO MCP connection lifecycle around session reset; done means /new loads the server without cancellation or requiring a manual reload.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- shell
- Domain
- cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100