Learn how to give GitHub Copilot more tools to expand the capabilities of your development workflow.
- Who is this for: Developers looking to enhance their AI-assisted workflows, GitHub Copilot users, and AI enthusiasts.
- What you'll learn: We'll introduce MCP basics, a GitHub MCP server setup, and integration with Copilot Agent Mode. Next, we'll MCP-ify our own API!
- What you'll be doing: A mixed development workflow that uses GitHub Copilot to manage issues while upgrading the extracurricular activities website for Mergington High School.
- Prerequisites: Basic knowledge of GitHub Copilot. If you don't have that yet, first do the Getting Started with Copilot exercise.
- How long: This exercise takes about one hour to complete.
In this exercise, you will:
- Integrate a GitHub MCP server with GitHub Copilot.
- Delegate Copilot to research similar projects and open issues.
- Ask Copilot to find an important issue and implement it from idea to pull request.
- Add comments to a recently closed issue.
- Learn how to use your own API as an MCP server.
Important
This exercise assumes basic knowledge of GitHub Copilot. If you are unfamiliar, we recommend the Getting Started with Copilot exercise.
Simply copy the exercise to your account, then give your favorite Octocat (Mona) about 20 seconds to prepare the first lesson, then refresh the page.
When copying the exercise, we recommend the following settings:
- For owner, choose your personal account or an organization to host the repository.
- We recommend creating a public repository, since private repositories will use Actions minutes.
If the exercise isn't ready in 20 seconds, please check the Actions tab.
- Check to see if a job is running. Sometimes it simply takes a bit longer.
- If the page shows a failed job, please submit an issue. Nice, you found a bug! 🐛
© 2025 GitHub • Code of Conduct • MIT License