github / github/copilot-cli

/new fails to load STDIO MCP and requires /mcp reload

Open
#4,811 0 comments 0 reactions 0 assignees View on GitHub

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
  1. In an existing Copilot CLI session, type /new
  2. 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
  1. 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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.