Skip to main content

Extending Copilot coding agent with the Model Context Protocol (MCP)

Learn how to use the Model Context Protocol (MCP) to extend the capabilities of Агент кодирования Copilot.

Примечание.

Агент кодирования Copilot находится в public preview и подлежит изменению. Во время предварительной версии использование функции подлежит Условия лицензии GitHub Pre-release.

Prerequisite

Before setting up an MCP server for Агент кодирования Copilot, read Model Context Protocol (MCP) and Агент кодирования Copilot to make sure you understand the concepts around MCP servers and Агент кодирования Copilot.

Introduction

As a repository administrator, you can configure MCP servers for use within your repository. You do this using a JSON-formatted configuration that specifies the details of the MCP servers you want to use. You enter the JSON configuration directly into the settings for the repository on GitHub.com.

Предупреждение

Once you've configured an MCP server, Copilot will be able to use the tools provided by the server autonomously, and will not ask for your approval before using them.

Adding an MCP configuration to your repository

Repository administrators can configure MCP servers by following these steps:

  1. На GitHubперейдите на главную страницу репозитория.

  2. Под именем репозитория щелкните Settings. Если вкладка "Параметры" не отображается, выберите раскрывающееся меню и нажмите кнопку "Параметры".

    Снимок экрана: заголовок репозитория с вкладками. Вкладка "Параметры" выделена темно-оранжевым контуром.

  3. In the "Code & automation" section of the sidebar, click Copilot then Coding agent.

  4. Add your configuration in the MCP configuration section.

    The following sections in this article explain how to write the JSON configuration that you need to enter here.

  5. Click Save.

    Your configuration will be validated to ensure proper syntax.

  6. If your MCP server requires a key or secret, add a secret to your Copilot environment. Only secrets with names prefixed with COPILOT_MCP_ will be available to your MCP configuration. See Setting up a Copilot environment for Агент кодирования Copilot.

Writing a JSON configuration for MCP servers

You configure MCP servers using a special JSON format. The JSON must contain an mcpServers object, where the key is the name of the MCP server (for example, sentry), and the value is an object with the configuration for that MCP server.

JSON
{
  "mcpServers": {
    "MCP SERVER 1": {
      "command": "VALUE",
      "args": [ VALUES ],
      ...
    },
    "MCP SERVER 2": {
      "command": "VALUE",
      "args": [ VALUES ],
      ...
    },
    ...
  }
}

The configuration object can contain the following keys:

Required keys for local and remote MCP servers

  • tools (string[]): The tools from the MCP server to enable. You may be able to find a list of tools in the server's documentation, or in its code. We strongly recommend that you allowlist specific read-only tools, since the agent will be able to use these tools autonomously and will not ask you for approval first. You can also enable all tools by including * in the array.
  • type (string): Агент кодирования Copilot accepts "local", "http", or "sse".

Local MCP specific keys

  • command (string): Required. The command to run to start the MCP server.
  • args (string[]): Required. The arguments to pass to the command.
  • env (object): Optional. The environment variables to pass to the server. This object should map the name of the environment variable that should be exposed to your MCP server to either of the following:
    • The name of a GitHub Actions secret you have configured, beginning with COPILOT_MCP_.
    • A string value.

Remote MCP specific keys

  • url (string): Required. The MCP server's URL.
  • headers (object): Optional. The headers to attach to requests to the server. This object should map the name of header keys to either of the following:
    • The name of a GitHub Actions secret you have configured, beginning with COPILOT_MCP_ preceded by a $
    • A string value

Example configurations

Example: Sentry

The Sentry MCP server gives Copilot authenticated access to exceptions recorded in Sentry.

JavaScript
// If you copy and paste this example, you will need to remove the comments prefixed with `//`, which are not valid JSON.
{
  "mcpServers": {
    "sentry": {
      "type": "local",
      "command": "npx",
      // We can use the $SENTRY_HOST environment variable which is passed to
      // the server because of the `env` value below.
      "args": ["@sentry/mcp-server@latest", "--host=$SENTRY_HOST"],
      "tools": ["get_issue_details", "get_issue_summary"],
      "env": {
        // We can specify an environment variable value as a string...
        "SENTRY_HOST": "https://contoso.sentry.io",
        // or refer to a GitHub Actions secret with a name starting with
        // `COPILOT_MCP_`
        "SENTRY_ACCESS_TOKEN": "COPILOT_MCP_SENTRY_ACCESS_TOKEN"
      }
    }
  }
}

Example: Notion

The Notion MCP server gives Copilot authenticated access to notes and other content from Notion.

JavaScript
// If you copy and paste this example, you will need to remove the comments prefixed with `//`, which are not valid JSON.
{
  "mcpServers": {
    "notionApi": {
      "type": "local",
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        // We can use the $NOTION_API_KEY environment variable which is passed to
        // the server because of the `env` value below.
        "OPENAPI_MCP_HEADERS={\"Authorization\": \"Bearer $NOTION_API_KEY\", \"Notion-Version\": \"2022-06-28\"}",
       "mcp/notion"
      ],
      "env": {
        // The value of the `COPILOT_MCP_NOTION_API_KEY` secret will be passed to the
        // server command as an environment variable called `NOTION_API_KEY`
        "NOTION_API_KEY": "COPILOT_MCP_NOTION_API_KEY"
      },
      "tools": ["*"]
    }
  }
}

Example: Azure

The Azure MCP server creates a seamless connection between Copilot and key Azure services such as Azure Cosmos DB and the Azure Storage platform.

To use the Azure MCP with Агент кодирования Copilot, you must update the repository's copilot-setup-steps.yml file to include an Azure login workflow step.

  1. Configure OIDC in a Microsoft Entra application, trusting GitHub. See Use the Azure Login action with OpenID Connect.

  2. Add a .github/workflows/copilot-setup-steps.yml Actions workflow file in your repository if you do not already have one.

  3. Add an Azure login step to the copilot-setup-steps workflow job.

    YAML
    on:
      workflow_dispatch:
    permissions:
      id-token: write
      contents: read
    jobs:
      copilot-setup-steps:
        runs-on: ubuntu-latest
        permissions:
          id-token: write
          contents: read
        environment: copilot
        steps:
          - name: Azure login
            uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5
            with:
              client-id: ${{ secrets.AZURE_CLIENT_ID }}
              tenant-id: ${{ secrets.AZURE_TENANT_ID }}
              subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
    

    This configuration ensures the azure/login action is executed when Агент кодирования Copilot runs.

  4. In your repository’s Copilot environment, add secrets for your AZURE_CLIENT_ID, AZURE_TENANT_ID and AZURE_SUBSCRIPTION_ID.

  5. Configure the Azure MCP server by adding an azure object to your MCP configuration.

JSON
 {
   "mcpServers": {
     "Azure": {
      "type": "local",
      "command": "npx",
      "args": [
        "-y",
        "@azure/mcp@latest",
        "server",
        "start"
       ],
      "tools": ["*"]
     }
   }
 }

Example: Cloudflare

The Cloudflare MCP server creates connections between your Cloudflare services, including processing documentation and data analysis.

JSON
{
  "mcpServers": {
    "cloudflare": {
      "type": "sse",
      "url": "https://docs.mcp.cloudflare.com/sse",
      "tools": ["*"]
    }
  }
}

Reusing your MCP configuration from Visual Studio Code

If you have already configured MCP servers in VS Code, you can leverage a similar configuration for Агент кодирования Copilot.

Depending on how VS Code is configured, you may be able to find your MCP settings in your repository's .vscode/mcp.json file, or in your machine's private settings.json file.

To adapt the configuration for Агент кодирования Copilot, you will need to:

  1. Add a tools key for each MCP server, specifying which tools will be available to Copilot.
  2. If you've configured inputs, switch to using env directly.
  3. If you've configured an envFile, switch to using env directly.
  4. Update any references to inputs in your args configuration to refer to environment variables from env instead.

For more information on MCP in VS Code, see the VS Code docs.

Setting up a Copilot environment for Агент кодирования Copilot

Some MCP servers will require keys or secrets. To leverage those servers in Агент кодирования Copilot, you can add secrets to an environment for Copilot. This ensures the secrets are properly recognized and passed to the applicable MCP server that you have configured.

You must be a repository administrator to configure a Copilot environment for your repository.

  1. На GitHubперейдите на главную страницу репозитория.

  2. Под именем репозитория щелкните Settings. Если вкладка "Параметры" не отображается, выберите раскрывающееся меню и нажмите кнопку "Параметры".

    Снимок экрана: заголовок репозитория с вкладками. Вкладка "Параметры" выделена темно-оранжевым контуром.

  3. На левой боковой панели щелкните Среды.

  4. Выберите Новая среда.

  5. Call the new environment copilot and click Configure environment.

  6. Under "Environment secrets", click Add environment secret.

  7. Give the secret a name beginning COPILOT_MCP_, add the secret value, then click Add secret.

Validating your MCP configuration

Once you've set up your MCP configuration, you should test it to make sure it is set up correctly.

  1. Create an issue in the repository, then assign it to Copilot.
  2. Wait a few seconds, and Copilot will leave an 👀 reaction on the issue.
  3. Wait a few more seconds, and Copilot will create a pull request, which will appear in the issue's timeline.
  4. Click the created pull request in the timeline, and wait until a "Copilot started work" timeline event appears.
  5. Click View session to open the Агент кодирования Copilot logs.
  6. Click the ellipsis button (...) at the top right of the log viewer, then click Copilot in the sidebar.
  7. Click the Start MCP Servers step to expand the logs.
  8. If your MCP servers have been started successfully, you will see their tools listed at the bottom of the logs.

If your MCP servers require any dependencies that are not installed on the GitHub Actions runner by default, such as uv and pipx, or that need special setup steps, you may need to create a copilot-setup-steps.yml Actions workflow file to install them. For more information, see Customizing the development environment for Copilot coding agent.

Customizing the built-in GitHub MCP server

The GitHub MCP server is enabled by default and connects to GitHub with a specially scoped token that only has read-only access to the current repository.

If you want to allow Copilot to access data outside the current repository, you can give it a personal access token with wider access.

  1. Create a personal access token with the appropriate permissions. We recommend using a fine-grained personal access token, where you can limit the token's access to read-only permissions on specific repositories. For more information on personal access tokens, see Управление личными маркерами доступа.

  2. На GitHubперейдите на главную страницу репозитория.

  3. Под именем репозитория щелкните Settings. Если вкладка "Параметры" не отображается, выберите раскрывающееся меню и нажмите кнопку "Параметры".

    Снимок экрана: заголовок репозитория с вкладками. Вкладка "Параметры" выделена темно-оранжевым контуром.

  4. In the "Code & automation" section of the sidebar, click Copilot then Coding agent.

  5. Add your configuration in the MCP configuration section.

  6. Click Save.

  7. На левой боковой панели щелкните Среды.

  8. Click the copilot environment.

  9. Under "Environment secrets", click Add environment secret.

  10. Call the secret COPILOT_MCP_GITHUB_PERSONAL_ACCESS_TOKEN, enter your personal access token in the "Value" field, then click Add secret.

For information on using the GitHub MCP server in other environments, see Using the GitHub MCP Server.

Next steps