Summary

The auth_login tool now provides comprehensive session information in its success response, giving the model immediate context about the authenticated user and server configuration without requiring an additional get_me tool call.

Why

Eliminates wasteful get_me tool call after authentication. Provides the model with a "warm start" by including user details and configuration directly in the auth_login response text that the model receives.

What changed

• AddedGetSessionInfo callback toAuthToolDependencies to generate session context after authentication
• ModifiedpollAndComplete function to fetch and include user info and configuration in auth_login success message
• Auth_login response now includes formatted session information with:
  • User account details (username, name, email, company, location, profile URL)
  • Enabled toolsets and tools
  • Configuration flags (read-only, lockdown, dynamic toolsets)
• Removed "Call get_me to see who you're logged in as" from auth_login success message (no longer needed)

MCP impact

• No tool or API changes
• Tool schema or behavior changed
• New tool added

The auth_login tool's response text now includes comprehensive session information. No schema changes, but the response content is significantly enhanced.

Prompts tested (tool changes only)

N/A - This change enhances the existing auth_login tool's response without altering its invocation or parameters.

Security / limits

• No security or limits impact
• Auth / permissions considered
• Data exposure, filtering, or token/size limits considered

User info is fetched using the authenticated token and only included in the auth_login response after successful authentication. Reuses existing get_me endpoint with same permissions.

Lint & tests

• Linted locally with./script/lint
• Tested locally with./script/test

Docs

• Not needed
• Updated (README / docs / examples)

The enhanced response is part of the auth_login tool output and doesn't require documentation changes.

Example

After successful authentication, the auth_login tool returns:

✅ Successfully authenticated with GitHub!All GitHub tools are now available.## Your GitHub Account**Username:** @octocat**Name:** The Octocat**Email:** octocat@github.com**Company:** GitHub**Location:** San Francisco**Profile:** https://github.com/octocat## Server Configuration**Enabled Toolsets:** context, repos, issues, pull_requests, users**Configuration:**- Read-only mode (if enabled)- Lockdown mode (if enabled)- Dynamic toolsets (if enabled)

This information is provided directly in the tool response text, which the model receives as part of the conversation, giving it immediate context without requiring a follow-up get_me call.

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn moreCopilot coding agent tips in the docs.