# Connect the MultitaskAI MCP server to goose

goose adds remote MCP servers as extensions. Add MultitaskAI as a Remote Extension (Streamable HTTP) with your API key as a request header.

## Endpoint

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

## Steps

1. Create an API key in your MultitaskAI account.
2. Click the button at the top left to open the sidebar, then click Extensions.
3. Click Add custom extension and set Type to Remote Extension (Streamable HTTP).
4. Enter multitaskai as the name, paste the URL below as the Endpoint URL and add the request header below, with your key in place of YOUR_API_KEY, then click Add.
5. Open a chat and check that the MultitaskAI tools are available.

```text
Type: Remote Extension (Streamable HTTP)
Endpoint URL: https://mcp.multitaskai.com
Custom Request Header: Authorization: Bearer YOUR_API_KEY
```

## Authentication

goose 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

- goose is now maintained by the Agentic AI Foundation, and its docs live at goose-docs.ai.
- In the CLI, run goose configure, choose Add Extension, then Remote Extension (Streamable HTTP), and answer yes to custom headers.
- The config file is ~/.config/goose/config.yaml on macOS and Linux and %APPDATA%\Block\goose\config\config.yaml on Windows.
- OAuth also works without a header, and SSE is no longer supported.

## Official documentation

The [Agentic AI Foundation MCP documentation](https://goose-docs.ai/docs/getting-started/using-extensions) covers goose's own settings in detail. See the [overview](/docs.md) for the endpoint and authentication, and [pricing](/pricing/) for the daily free requests.
