# Connect the MultitaskAI MCP server to Google ADK

Google's Agent Development Kit builds agents in Python. Add MultitaskAI as an McpToolset with Streamable HTTP connection parameters and your API key.

## Endpoint

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

## Steps

1. Create an API key in your MultitaskAI account.
2. Add the McpToolset below to your agent's tools, with your key in place of YOUR_API_KEY.
3. Run adk web from the parent folder of your agent, select the agent and ask which MultitaskAI tools it can use.

```python
from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams

root_agent = LlmAgent(
    model="gemini-flash-latest",
    name="assistant",
    instruction="Use the MultitaskAI tools to help the user.",
    tools=[
        McpToolset(
            connection_params=StreamableHTTPConnectionParams(
                url="https://mcp.multitaskai.com",
                headers={"Authorization": "Bearer YOUR_API_KEY"},
            )
        )
    ],
)
```

## Authentication

Google ADK 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

- The ADK docs moved to adk.dev.
- Headers go on StreamableHTTPConnectionParams; auth_scheme and auth_credential are available for managed auth.
- In TypeScript, use MCPToolset from @google/adk with the headers in transportOptions.requestInit.headers.

## Official documentation

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