GitHub Copilot’s Customize Tab Is Now Generally Available
GitHub Copilot's new Customize tab is generally available, bringing MCP servers, plugins, skills, and canvases into one place inside the Copilot app.
GitHub has shipped the Customize tab in the GitHub Copilot app to general availability. The tab puts MCP servers (external tool integrations), plugins, skills, and canvases into a single browsable view. Teams can now discover featured customizations, browse by category, and connect the tools they already use directly inside Copilot, without digging through separate settings or third-party documentation.
What happened
| Detail | Fact |
|---|---|
| Feature | Customize tab in the GitHub Copilot app |
| Status | Generally available |
| Announced | August 25, 2026 |
| Customization types covered | MCP servers, plugins, skills, canvases |
| Featured DevOps integration | Azure DevOps backlog triage and delegation |
GitHub’s Copilot app now has a dedicated Customize tab, available to all users. Before this release, connecting external tools, adding skills, or setting up canvases required navigating separate areas of the app. The new tab collects everything into one screen.
The tab is organized around four customization types: MCP servers (the Model Context Protocol standard that lets Copilot call external tools and APIs), plugins, skills, and canvases (persistent work surfaces that keep relevant context visible while you act on it).
What’s inside the Customize tab?
A Featured view greets you when you open the tab. According to GitHub, this is designed for the common situation where you know you want to extend Copilot but are not sure which specific server, plugin, or canvas to reach for first. Featured picks are drawn from across all four categories.
Beyond the Featured view, each customization type gets its own browsable section. MCP servers in particular now have a trending list and category filters, which should make it faster to find integrations for specific tools.
Azure DevOps backlog delegation
One of the highlighted use cases is Azure DevOps integration. From the Customize tab, teams can triage issues, prioritize backlogs, assign follow-ups, and then hand the work to Copilot to investigate, implement, or prepare for code review. This positions Copilot less as a code-completion tool and more as an agent that can own a task end to end.
Why it matters
The Customize tab is a small UI change with a meaningful implication: GitHub is betting that the value of Copilot is not just in the base model but in how well it connects to your existing stack. Centralizing discovery lowers the friction of actually setting up those connections, which is currently the main reason teams do not bother.
For developers already working inside the Copilot app, this reduces context switching. For team leads, the Azure DevOps delegation feature is the first clear signal that GitHub intends Copilot to handle project management tasks, not just write code. That is a broader surface area than most teams are currently using. Our earlier look at what holds companies back from scaling multi-agent AI found that discoverability and integration friction are consistently cited as top blockers, which is exactly what this tab is trying to address.
Our take
A consolidated discovery surface is genuinely useful. Most teams we work with have heard of MCP servers but have not set any up because it felt like extra configuration work with uncertain payoff. A curated Featured view with trending options changes that calculus a little.
The Azure DevOps backlog delegation feature is worth testing, but treat it as a prototype workflow rather than a production handoff. Copilot can prepare a task for review, but a human still needs to verify the output before it ships. The framing of “delegate to Copilot” is accurate for low-stakes triage; it is premature for anything touching production code or customer-facing issues without a review step.
If you are already using Copilot and are looking to get more from it, the Customize tab is the right place to start. If you are evaluating whether to bring AI tooling into your development workflow at all, our AI integration service covers how to connect tools like this to your existing stack without creating new maintenance headaches.
What to do about it
- Open the GitHub Copilot app and select the Customize tab to see what is available.
- Browse the Featured view first: it surfaces the most relevant starting points without requiring you to know the MCP ecosystem in advance.
- Check the MCP servers section for tools your team already uses (issue trackers, CI systems, documentation tools).
- If your team uses Azure DevOps, test the backlog triage delegation on a non-critical backlog before relying on it for active sprints.
- Revisit your setup every few weeks: the trending MCP server list will change as the ecosystem matures.
Start with the Featured view, pick one integration that connects a tool you already use daily, and measure whether it actually saves time before adding more.
Frequently asked questions
What is the Customize tab in GitHub Copilot?
It is a new tab in the GitHub Copilot app that brings MCP servers, plugins, skills, and canvases together in one place, making it easier to discover and set up customizations without navigating separate settings.
What are MCP servers in GitHub Copilot?
MCP servers (Model Context Protocol servers) are external tool integrations that allow Copilot to call outside tools and APIs. The Customize tab lets you browse trending MCP servers and filter them by category.
Can GitHub Copilot manage Azure DevOps backlogs?
Yes. Through the Customize tab, teams can triage issues, prioritize backlogs, assign follow-ups, and delegate tasks to Copilot to investigate, implement, or prepare for review.
How do I access the GitHub Copilot Customize tab?
Open the GitHub Copilot app and select Customize. If you do not have the app installed, install the GitHub Copilot app first, then open the Customize tab to browse featured and categorized customizations.
