# Connect the MultitaskAI MCP server to Strands Agents

Strands Agents is an AWS SDK for building agents in Python. Create an MCPClient for MultitaskAI with an Authorization header and give it to your agent.

## Endpoint

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

## Steps

1. Create an API key in your MultitaskAI account.
2. Create the MCPClient below, with your key in place of YOUR_API_KEY.
3. Pass the client to your agent's tools, then ask the agent which MultitaskAI tools it can use.

```python
from strands import Agent
from strands.tools.mcp import MCPClient

multitaskai = MCPClient(
    url="https://mcp.multitaskai.com",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
)
agent = Agent(tools=[multitaskai])
```

## Authentication

Strands Agents 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

- Pass the client directly with Agent(tools=[mcp_client]).
- Or open it in a with mcp_client: block and list its tools with list_tools_sync().
- The TypeScript SDK uses StreamableHTTPClientTransport with headers in requestInit.

## Official documentation

The [AWS MCP documentation](https://strandsagents.com/docs/user-guide/sdk/tools/mcp-transports/) covers Strands Agents's own settings in detail. See the [overview](/docs.md) for the endpoint and authentication, and [pricing](/pricing/) for the daily free requests.
