Model Context Protocol (MCP) and GitHub Copilot coding agent

Find out about using the Model Context Protocol (MCP) with Agente de codificación de Copilot.

En este artículo

Nota:

Agente de codificación de Copilot se encuentra en versión preliminar pública y está sujeto a cambios. Durante la versión preliminar, el uso de la característica está sujeto a Términos de licencia de la versión preliminar de GitHub.

Overview

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 Agente de codificación de Copilot by connecting it to other tools and services.

The agent can use tools provided by local and remote MCP servers. Some MCP servers are configured by default to provide the best experience for getting started.

For more information on MCP, see the official MCP documentation. For information on some of the currently available MCP servers, see the MCP servers repository.

Nota:

  • Agente de codificación de Copilot only supports tools provided by MCP servers. It does not support resources or prompts.
  • Agente de codificación de Copilot does not currently support remote MCP servers that leverage OAuth for authentication and authorization.

Default MCP servers

The following MCP servers are configured automatically for Agente de codificación de Copilot:

  • GitHub: The GitHub MCP server gives Copilot access to GitHub data like issues and pull requests. To learn more, see Uso del servidor MCP de GitHub.

  • Playwright: The Playwright MCP server gives Copilot access to web pages, including the ability to read, interact and take screenshots.

    • By default, the Playwright MCP server is only able to access web resources hosted within Copilot's own environment, accessible on localhost or 127.0.0.1.

Setting up MCP servers in a repository

Repository administrators can configure MCP servers for use within that repository. This is done via a JSON-formatted configuration that specifies the details of the MCP servers that Agente de codificación de Copilot can use.

Once MCP servers are configured for use within a repository, the tools specified in the configuration will be available to Agente de codificación de Copilot during each assigned task.

Copilot will use available tools autonomously, and will not ask for approval before use.

For details of how to set up MCP servers for Agente de codificación de Copilot in a repository, see Extensión del agente de codificación de Copilot con el protocolo de contexto de modelo (MCP).

Best practices

  • Enabling third-party MCP servers for use may impact the performance of the agent and the quality of the outputs. Review the third-party MCP server thoroughly and ensure that it meets your organization’s requirements.

  • By default, Agente de codificación de Copilot does not have access to write MCP server tools. However, some MCP servers do contain such tools. Be sure to review the tools available in the MCP server you want to use. Update the tools field in the MCP configuration with only the necessary tooling.

  • Carefully review the configured MCP servers prior to saving the configuration to ensure the correct servers are configured for use.