# Connect the MultitaskAI MCP server to Gemini CLI

Gemini CLI reads MCP servers from settings.json. Add MultitaskAI under httpUrl with 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 for every project, or .gemini/settings.json in one project.
3. Add the server below, with your key in place of YOUR_API_KEY, and save the file.
4. Start Gemini CLI and run /mcp to check that MultitaskAI shows as CONNECTED.

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

## Authentication

Gemini CLI 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

- Use httpUrl for Streamable HTTP; url is for SSE servers.
- You can also run gemini mcp add --transport http with an Authorization header; add --scope user to use it in every project.
- Since 2026-06-18 Google has replaced Gemini CLI with Antigravity CLI for unpaid, Google AI Pro and Ultra and Google One users; it stays available with paid Gemini API keys and Gemini Code Assist Standard and Enterprise.
- Run gemini mcp list from a shell to check the server.

## Official documentation

The [Google MCP documentation](https://geminicli.com/docs/tools/mcp-server/) covers Gemini CLI's own settings in detail. See the [overview](/docs.md) for the endpoint and authentication, and [pricing](/pricing/) for the daily free requests.
