First of all, really appreciate the work you've put into this so far and the transparency in mentioning a remote version will be available soon.

This question is for me to understand what changes you'll make to the authentication flow for the remote server. Will it require a PAT to be managed by the user in their config as it is for the existing server? Or will you natively support something like GitHub Apps through the MCP authorization spec for users to be able to log in with a consent flow in their browser?

Additional context for my use case: I'm investigating how to offer an MCP server tied to a GHES instance with multiple Organizations, where users may have access to many of those Orgs.