# Connect the MultitaskAI MCP server to Gemini Code Assist

Gemini Code Assist agent mode in VS Code reads MCP servers from ~/.gemini/settings.json. Add MultitaskAI with its URL and your API key in the headers.

## Endpoint

```text
https://mcp.multitaskai.com
```

## Steps

1. Create an API key in your MultitaskAI account.
2. Open ~/.gemini/settings.json.
3. Add the server below, with your key in place of YOUR_API_KEY, and save the file.
4. Run Developer: Reload Window from the Command Palette, then type /mcp in agent mode to check that MultitaskAI is connected.

```json
{
  "mcpServers": {
    "multitaskai": {
      "httpUrl": "https://mcp.multitaskai.com",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

## Authentication

Gemini Code Assist sends your MultitaskAI API key in the Authorization header. Create a key in your account and use it in place of YOUR_API_KEY. Keep the key out of files you share or commit.

```text
Authorization: Bearer YOUR_API_KEY
```

## Good to know

- Agent mode is marked Preview.
- It reads the same ~/.gemini/settings.json as Gemini CLI, so a server added there already shows up.
- Reload the window after saving, then type /mcp in agent mode to check the connection.
- This setup covers VS Code; JetBrains IDEs use a different file and do not support /mcp.

## Official documentation

The [Google MCP documentation](https://docs.cloud.google.com/gemini/docs/codeassist/use-agentic-chat-pair-programmer) covers Gemini Code Assist's own settings in detail. See the [overview](/docs.md) for the endpoint and authentication, and [pricing](/pricing/) for the daily free requests.
