Four developer-tool modules connecting into a central customization tray
Four developer-tool modules connecting into a central customization tray
+ Microsoft News

GitHub Copilot app Customize tab becomes generally available

GitHub made the Copilot app Customize tab generally available, bringing MCP servers, plugins, skills, and canvases into one extension surface.

GitHub has made the Customize tab in the GitHub Copilot app generally available, giving users one place to discover MCP servers, plugins, skills, and canvases.

The company says the tab includes featured customizations, browsing by type, and faster discovery for MCP servers through trending options and categories. The stated goal is to help teams connect Copilot to the tools, knowledge, and workflows they already use.

The release is small in UI terms but important in product direction. Copilot is becoming less like a fixed chat surface and more like an agent runtime whose behavior depends on installed tools, skills, canvases, and governed extension sources.

Customization is moving into the app shell

The Customize tab follows GitHub’s Agent Plugins 1.0 release earlier this month. That standard packages agent skills and MCP servers into one installable plugin, with Copilot-specific behavior kept in a namespaced directory.

That matters because agent customization has been fragmented. Teams may have MCP servers for internal systems, prompt skills for workflows, canvases for task-specific context, and client-specific extension formats. A single app surface does not solve governance by itself, but it makes the extension layer visible to users and administrators.

GitHub says the tab can highlight featured customizations from across the Copilot app and let users browse dedicated sections for each type. One example in the announcement is an Azure DevOps backlog canvas that helps triage issues, prioritize work, assign follow-ups, and hand implementation tasks to Copilot.

The practical shift is that the agent’s capabilities are no longer only a model-picker decision. They also depend on which tools and workflow objects are installed, approved, and discoverable at the moment of work.

Extension governance becomes part of agent governance

Agent Plugins 1.0 already pointed toward centralized controls. GitHub’s plugin announcement said Copilot Business and Enterprise customers can use managed settings to install or block plugins, add known marketplaces, and restrict installation to managed marketplaces across supported Copilot clients.

That is the necessary counterpart to easier discovery. If users can add MCP servers and skills with little friction, organizations need a clear policy layer for which servers can touch production systems, which plugins can run commands, and which canvases can expose sensitive context.

The Customize tab gives the user-facing side of that system a home. The enterprise question is whether the approval, inventory, and audit layers keep up with discovery.

Sources

The AI Feed Desk

The AI Feed Desk

Editorial desk

The AI Feed Desk tracks AI provider updates, model releases, agent tooling, and enterprise adoption, turning fast-moving announcements into source-linked context for builders and operators.

Noticed a typo, incorrect information, or translation error?

Tell us so we can fix it.

Help Improve This Article

Related Articles

A developer workbench shows completed agent requests with model labels, credit meters, cache indicators, and session branches

GitHub Copilot Auto now shows model and AI-credit details

GitHub Copilot's weekly release adds model, AI-credit, and cache visibility for Auto requests plus new CLI session controls.

The AI Feed Desk

By The AI Feed Desk

An enterprise admin console connects approved plugins, MCP servers, telemetry, and IDE agent permissions into one controlled developer workspace

GitHub brings managed Copilot settings to JetBrains

GitHub Copilot for JetBrains now supports enterprise-managed controls for plugins, MCP servers, telemetry routing, and agent permission modes.

The AI Feed Desk

By The AI Feed Desk

A small coding model module routes glowing code paths to laptops, phones, IDE panels, and command-line surfaces

MAI-Code-1-Flash moves across GitHub Copilot before enterprise access

GitHub says Microsoft's small coding model is expanding across Copilot CLI, app, chat, IDE, mobile, and Xcode surfaces before Business and Enterprise rollout.

The AI Feed Desk

By The AI Feed Desk

A pull request review panel connects to Jira cards and a guarded plugin marketplace

GitHub turns Copilot governance into a code-review and Jira story

GitHub's June 25 Copilot updates pair cheaper code-review analysis with Jira agent visibility and stricter controls over plugin marketplaces.

The AI Feed Desk

By The AI Feed Desk

A JetBrains-style coding workspace lets a user choose between agent providers, hooks, and MCP tools

GitHub adds Codex as a JetBrains Copilot agent provider

GitHub added Codex as a public-preview agent provider in JetBrains Copilot, alongside hooks, MCP server management, approval modes, Claude permissions, debug logs, and custom models.

The AI Feed Desk

By The AI Feed Desk