Skip to content

Conversation

@JeanMertz
Copy link
Collaborator

Update the MCP server configuration logic to use a HashSet instead of a Vec when identifying active servers. This change ensures that each unique MCP server is only processed once, preventing potential duplicate connections.

The run_services method in jp_mcp now accepts an owned HashSet, reducing the need for explicit cloning during the service startup loop. Additionally, this commit fixes a logging bug in the MCP environment variable loader by correctly using inspect_err and formatting the error output.

Update the MCP server configuration logic to use a `HashSet` instead of
a `Vec` when identifying active servers. This change ensures that each
unique MCP server is only processed once, preventing potential duplicate
connections.

The `run_services` method in `jp_mcp` now accepts an owned `HashSet`,
reducing the need for explicit cloning during the service startup loop.
Additionally, this commit fixes a logging bug in the MCP environment
variable loader by correctly using `inspect_err` and formatting the
error output.

Signed-off-by: Jean Mertz <git@jeanmertz.com>
Signed-off-by: Jean Mertz <git@jeanmertz.com>
@JeanMertz JeanMertz merged commit f1c18d4 into main Feb 2, 2026
12 checks passed
@JeanMertz JeanMertz deleted the improve-tool-inquery52 branch February 2, 2026 20:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant