VQV Signal

PRODUCT UPDATE RISING TECHNICAL

Copilot usage metrics API now shows names of custom skills, agents and MCP servers

According to a GitHub Changelog entry, Copilot usage metrics now show the names of the skills, custom agents, Model Context Protocol (MCP) servers, slash commands, and plugins that an organization creates. The snippet says this replaces grouping those items under a broader heading, but it is cut off before describing that grouping in full. The entry is dated October 22, 2026, based on its URL. The snippet does not include further technical details.

Source: GitHub Changelog · github.blog Published 2026-10-22T22:19:17+00:00 Detected 2026-10-23T01:18:47+00:00
View original source

According to a GitHub Changelog entry, Copilot usage metrics now show the names of the skills, custom agents, Model Context Protocol (MCP) servers, slash commands, and plugins that an organization creates. The snippet says this replaces grouping those items under a broader heading, but it is cut off before describing that grouping in full. The entry is dated October 22, 2026, based on its URL. The snippet does not include further technical details.

AI-assisted summary based on the listed source.

Copilot usage metrics now show the names of the skills, custom agents, Model Context Protocol (MCP) servers, slash commands, and plugins that your organization creates, instead of grouping them under… The post Custom skills, agents, and MCP servers in usage metrics API appeared first on <a...

Organizations that build their own Copilot skills, agents, or MCP servers can now track usage of each item by name in the metrics API. Teams measuring adoption of internal tooling should be able to see which items are used instead of relying on grouped totals. Readers should check the full changelog for availability details and how the data is returned.

Developers may have a new tool, API, or workflow change worth testing against their own stack.

Signal Strength 95% Technical label RISING Public Interest 52 Category PRODUCT UPDATE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 51 Practical Impact Score 38 Novelty Interest Score 94 Consequence Score 34 Curiosity Score 16 Shareability Score 63

VQV surfaced this signal because it is recent, relevant to Consumer AI, connected to GitHub Changelog.