| title | About Model Context Protocol (MCP) | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| allowTitleToDifferFromFilename | true | |||||||||||||||||||||
| shortTitle | MCP | |||||||||||||||||||||
| intro | Model Context Protocol (MCP) is a protocol that allows you to extend the capabilities of {% data variables.product.prodname_copilot %} by integrating it with other systems. | |||||||||||||||||||||
| versions |
|
|||||||||||||||||||||
| contentType | concepts | |||||||||||||||||||||
| redirect_from |
|
|||||||||||||||||||||
| category |
|
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 {% data variables.product.prodname_copilot %} by integrating it with a wide range of existing tools and services. MCP works across all major {% data variables.product.prodname_copilot_short %} surfaces—whether you're working in an IDE, using {% data variables.copilot.copilot_cli %}, working in the {% data variables.copilot.github_copilot_app %}, or delegating tasks to an agent on {% data variables.product.prodname_dotcom_the_website %}. You can also use MCP to create new tools and services that work with {% data variables.product.prodname_copilot_short %}, allowing you to customize and enhance your experience.
For more information on MCP, see the official MCP documentation. For a curated list of MCP servers from partners and the community, see the {% data variables.product.github %} MCP Registry.
To learn how to configure and use MCP servers, see:
- AUTOTITLE for {% data variables.copilot.copilot_chat_short %} in your IDE
- AUTOTITLE for {% data variables.copilot.copilot_cli_short %}
- AUTOTITLE for repository MCP configuration on {% data variables.product.prodname_dotcom_the_website %}
- AUTOTITLE for information on MCP server support in the {% data variables.copilot.github_copilot_app %} {% data reusables.copilot.mcp.mcp-policy %}
MCP is supported across the following clients:
- IDEs: There is broad support for local MCP servers in clients such as {% data variables.product.prodname_vscode %}, JetBrains IDEs, Xcode, and others. Support for remote MCP servers is growing, with editors like {% data variables.product.prodname_vscode %}, {% data variables.product.prodname_vs %}, JetBrains IDEs, Xcode, Eclipse, Cursor, and Windsurf providing this functionality with OAuth or PAT. To find out if your preferred editor supports remote MCP servers, check the documentation for your specific editor.
- {% data variables.copilot.copilot_cli_short %}: {% data variables.copilot.copilot_cli %} supports both local and remote MCP servers. The {% data variables.product.github %} MCP server is built in and available without additional configuration.
- {% data variables.copilot.github_copilot_app %}: The {% data variables.copilot.github_copilot_app %} supports MCP servers configured in your repository or {% data variables.copilot.copilot_cli_short %} and lets you add additional MCP servers in app settings.
- {% data variables.copilot.copilot_cloud_agent %} and {% data variables.copilot.copilot_code-review_short %}: {% data variables.product.prodname_dotcom_the_website %} supports MCP servers configured at the repository level. The configuration applies to both {% data variables.copilot.copilot_cloud_agent %} and {% data variables.copilot.copilot_code-review_short %}. The {% data variables.product.github %} MCP server and Playwright MCP server are configured by default.
The {% data variables.product.github %} MCP server is a Model Context Protocol (MCP) server provided and maintained by {% data variables.product.github %}.
{% data variables.product.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 {% data variables.product.github %}’s context and AI capabilities.
- Enable cloud-based workflows that work from any device, without local setup.
- Invoke {% data variables.product.github %} tools, such as {% data variables.copilot.copilot_cloud_agent %} (requires {% data variables.product.prodname_copilot %} subscription) and {% data variables.product.prodname_code_scanning %} (requires {% data variables.product.prodname_GHAS %} subscription), to assist with code generation and security analysis.
To learn how to set up and use the {% data variables.product.github %} MCP server, see AUTOTITLE.
To find out whether your editor supports the {% data variables.product.github %} MCP server, and which connection and authentication methods are available, see Support by host application in the github/github-mcp-server repository.
You can access the {% data variables.product.github %} MCP server remotely through {% data variables.copilot.copilot_chat_short %} in {% data variables.product.prodname_vscode %} without any local setup. The remote server has access to additional toolsets only available in the remote {% data variables.product.github %} MCP server. For a list of such tools, see Additional toolsets in the github/github-mcp-server repository.
The {% data variables.product.github %} MCP server can also run locally in any MCP-compatible editor, if necessary.
Important
Always review the {% data variables.product.github %} MCP server repository at github/github-mcp-server for the latest toolsets and authoritative configuration guidance.
The {% data variables.product.github %} MCP server supports enabling or disabling specific groups of functionalities via toolsets. Toolsets allow you to control which {% data variables.product.github %} API capabilities are available to your AI tools.
Enabling only the toolsets you need improves your AI assistant's performance and security. Fewer tools means better tool selection accuracy and fewer errors. Disabling unused toolsets also frees up tokens in the AI's context window.
Toolsets do not only include tools, but also relevant MCP resources and prompts where applicable.
To learn how to configure toolsets for the {% data variables.product.github %} MCP server, see AUTOTITLE.
For all public repositories, and private repositories covered by {% data variables.product.prodname_GHAS %}, interactions with the {% data variables.product.github %} MCP server are secured by push protection, which blocks secrets in AI-generated responses and prevents them from being included in actions taken on your behalf. You can also proactively scan your code for exposed secrets from within your AI coding agent. For more information, see AUTOTITLE.
The {% data variables.product.github %} MCP Registry is a curated list of MCP servers from partners and the community. You can use the registry to discover new MCP servers and find ones that meet your specific needs. See the {% data variables.product.github %} MCP Registry.
Note
The {% data variables.product.github %} MCP Registry is currently in {% data variables.release-phases.public_preview %} and subject to change.
- AUTOTITLE—Add MCP servers to {% data variables.copilot.copilot_chat_short %} in your IDE
- AUTOTITLE—Configure repository MCP servers for {% data variables.copilot.copilot_cloud_agent %} and {% data variables.copilot.copilot_code-review_short %}
- AUTOTITLE—Set up the {% data variables.product.github %} MCP server
- AUTOTITLE—Use the {% data variables.product.github %} MCP server
- AUTOTITLE
- AUTOTITLE