Note
- MCP support is generally available (GA) in Copilot Chat for Visual Studio Code.
- MCP support for Copilot in Visual Studio, JetBrains, Eclipse, and Xcode is in public preview and is subject to change.
- The GitHub Pre-release License Terms apply only to Copilot in IDEs where MCP support is still in preview. GA terms apply when using MCP for Copilot in Visual Studio Code.
Overview of Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard that defines how applications share context with large language models (LLMs). MCP provides a standardized way to connect AI models to different data sources and tools, enabling them to work together more effectively.
You can use MCP to extend the capabilities of Copilot Chat by integrating it with a wide range of existing tools and services. For example, the GitHub MCP server allows you to use Copilot Chat in your IDE to perform tasks on GitHub. You can also use MCP to create new tools and services that work with Copilot Chat, allowing you to customize and enhance your experience.
For more information on MCP, see the official MCP documentation. For information on currently available MCP servers, see the MCP servers repository.
To learn how to configure and use MCP servers with Copilot Chat, see Extending Copilot Chat with the Model Context Protocol (MCP).
Enterprises and organizations can choose to enable or disable use of MCP for members of their organization or enterprise. See Managing policies and features for Copilot in your enterprise. The MCP policy only applies to members with Copilot Business, Copilot Enterprise, or Copilot licenses assigned by the organization or enterprise that configures the policy. Copilot Free, Copilot Pro, or Copilot Pro+ do not have their MCP access governed by this policy.
About the GitHub MCP server
The GitHub MCP server is a Model Context Protocol (MCP) server provided and maintained by GitHub.
GitHub MCP server can be used to:
- Automate and streamline code-related tasks.
- Connect third-party tools (like Cursor, Windsurf, or future integrations) to leverage GitHub’s context and AI capabilities.
- Enable cloud-based workflows that work from any device, without local setup.
You can access the GitHub MCP server remotely through Visual Studio Code, or other editors that support remote MCP; or you can run it locally in any MCP-compatible editor, allowing you to choose between the convenience of a hosted solution or the customizability of a self-hosted setup.
If you want to utilize the remote GitHub MCP server, you can do so in a few steps, without any local setup. This is particularly useful for users who want to quickly leverage GitHub’s AI capabilities without the overhead of managing a local MCP server.
Running the GitHub MCP server locally requires a bit more setup, but it allows for greater customization and control over your AI interactions.
To learn how to set up and use the GitHub MCP server, see Using the GitHub MCP Server.
Availability
There is currently broad support for local MCP servers in clients such as Visual Studio Code, JetBrains IDEs, XCode, and others.
Support for remote MCP servers is growing, with editors like Visual Studio Code (with OAuth or PAT), Visual Studio (PAT only), JetBrains IDEs (PAT only), Xcode (PAT only), Eclipse (PAT only), Windsurf (PAT only), and Cursor (PAT only) already providing this functionality.
To find out if your preferred editor supports remote MCP servers, check the documentation for your specific editor.