> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sendkit.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# GitHub Copilot

> Connect SendKit to GitHub Copilot in VS Code for AI-powered email management

[GitHub Copilot](https://github.com/features/copilot) supports MCP servers in agent mode, allowing you to connect SendKit directly to your VS Code workflow.

## Prerequisites

* VS Code with GitHub Copilot extension installed
* Copilot agent mode enabled
* A SendKit API key with **Full** permission

## Setup

<Steps>
  <Step title="Create the MCP configuration file">
    In your project root, create or edit `.vscode/mcp.json`:

    ```json theme={null}
    {
      "servers": {
        "sendkit": {
          "type": "http",
          "url": "https://mcp.sendkit.dev/sendkit",
          "headers": {
            "Authorization": "Bearer sk_your_api_key_here"
          }
        }
      }
    }
    ```

    <Note>
      Replace `sk_your_api_key_here` with your actual API key from the [SendKit dashboard](https://app.sendkit.dev).
    </Note>
  </Step>

  <Step title="Reload VS Code">
    Reload the window or restart VS Code to load the MCP configuration.
  </Step>

  <Step title="Verify the connection">
    Open Copilot Chat in agent mode and ask:

    ```
    List all my SendKit domains
    ```

    You should see Copilot use the SendKit tools to fetch your data.
  </Step>
</Steps>

<Tip>
  VS Code uses `"servers"` as the top-level key (not `"mcpServers"`). This is different from most other MCP clients.
</Tip>

## Global configuration

To make SendKit available across all projects, use the command palette and run **MCP: Open User Configuration** to add the server to your user-level settings.

## Example prompts

```
Create a sender called "Notifications" with username "notifications" on my domain
```

```
Show me all my email templates
```

```
What's my bounce rate in the last 24 hours?
```