Summary
GitHub's enterprise and organization reports now measure Copilot CLI skills, custom agents, MCP servers, slash commands and plugins. The impact dashboard and API also expose rolling 28-day engagement for code completion, agent edit, code review, cloud agent, CLI and app. Customer-defined names are privacy-grouped. MCP interaction counts measure connection attempts, including failures, rather than tool calls.
Why it matters
For platform teams, agent rollout can now be managed with feature-level adoption data instead of license assignment alone. The new fields help find useful automations and enablement gaps. Interpret MCP counts carefully because failed reconnects can look like engagement.
Technical details
| Cli Customizations | skills, custom agents, MCP servers, slash commands, plugins |
|---|---|
| Feature Window | rolling 28 days |
| Surfaces | completion, agent edit, active/passive review, cloud agent, CLI, app |
| Privacy | customer-defined names grouped |
| Mcp Caveat | interaction_count counts connection attempts, not tool calls |
Tags
GitHub-Copilotusage-metricsMCPskillsadoption