> ## 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.

# Gemini CLI

> Connect SendKit to Gemini CLI for AI-powered email management from the terminal

[Gemini CLI](https://github.com/google-gemini/gemini-cli) is Google's command-line AI assistant. You can connect it to SendKit's MCP server to manage your email infrastructure with natural language.

## Prerequisites

* Gemini CLI installed
* A SendKit API key with **Full** permission

## Setup

<Steps>
  <Step title="Open the settings file">
    Edit your Gemini CLI settings at `~/.gemini/settings.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "sendkit": {
          "httpUrl": "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>

    For project-level configuration, create `.gemini/settings.json` in your project root instead.
  </Step>

  <Step title="Restart Gemini CLI">
    Close and reopen Gemini CLI to load the new configuration.
  </Step>

  <Step title="Verify the connection">
    Ask Gemini to interact with your SendKit account:

    ```
    List all my SendKit senders
    ```
  </Step>
</Steps>

<Tip>
  Gemini CLI uses `"httpUrl"` for HTTP streaming servers (not `"url"`). The `"url"` field is used for SSE transport only.
</Tip>

## Example prompts

```
Create a new contact list called "Beta Users"
```

```
What's my sending reputation right now?
```

```
Validate the email address user@example.com
```
