Agentic CLI customizations now in the usage metrics API
GitHub has updated the Copilot usage metrics API to include granular telemetry for agentic CLI activities. The API now tracks usage data for skills, custom agents, Model Context Protocol (MCP) servers, slash commands, and plugins.
Verified State Diff
Impact & Verification Analysis
Enterprise administrators, platform engineers, and developers building custom Copilot extensions.
It enables organizations to measure the effectiveness and adoption of custom AI agents and MCP-based integrations, which is critical for managing the lifecycle and security of internal AI tooling.
Full Fact Overview
This update expands the observability layer for GitHub Copilot in the CLI environment. By exposing metrics for MCP servers and custom agentic workflows, GitHub is providing enterprise administrators and developers with the ability to quantify the adoption and performance of custom-built AI extensions. This shift moves the API from tracking generic CLI interactions to monitoring specific, modular agentic components, facilitating better ROI analysis for custom AI toolchains.