> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trysiren.io/llms.txt
> Use this file to discover all available pages before exploring further.

# QuickSend

> To send notification directly without setting up a workflow.

Need to send a critical update or one-off announcement? You can use Siren to send a notification without setting up a workflow. This lets you directly send messages to a user over your desired channel.
To send a message, you just need to include the channel, recipient details (matching that channel), and optionally a template name with variables, as shown below. The request must be authorized using your API key.
Once sent, Siren will return a `notificationId`, which you can use to check the message status or fetch replies
Here's a simplified example:

```json theme={null}
{
  "channel": "EMAIL",
  "recipient": {
    "email": "user@example.com"
  },
  "template": {
    "name": "welcome_template"
  },
  "templateVariables": {
    "firstName": "John",
    "offerCode": "ABCD123"
  }
}
```

<Note>
  If you are not using the default provider configured in the Siren account, you can specify which provider to use by adding the `providerIntegration` field in the request. Please take a look at [API Reference](/docs/API-Reference/CreateProviderIntegrationAPI) for the details.
</Note>

Once a message is sent, you can use the following endpoints to track it:

* `GET /message-status/{notificationId}` - Check whether the message was delivered, failed, or is still pending.
* `GET /get-reply/{notificationId}` - Fetch replies to a message (currently supported for Slack only). This includes main messages and threaded responses from users.
  These endpoints help you build a full feedback loop between your system, the provider, and the user. For the complete details, refer to  [API Reference](/docs/API-Reference/GetMessageRepliesAPI).
  You can also send notifications using **MCP**, **AI Agent Toolkit**, or **SDK**, depending on your system architecture.

### Using MCP (Model Context Protocol)

If you are using MCP to send a notification quickly, follow these steps:

<Steps>
  <Step title="Install or run the MCP server">
    You can either install it globally using `npm install -g @trysiren/mcp`, or run it directly with `npx -y @trysiren/mcp`.
  </Step>

  <Step title="Start the server with messaging tool enabled">
    Run the following command to enable the QuickSend tool:\
    `npx -y @trysiren/mcp --tools=messaging.send --api-key=YOUR_SIREN_API_KEY`
  </Step>

  <Step title="Configure your development environment">
    Connect your MCP-compatible environment (e.g., Claude, VS Code, Replit, Cursor) to the running MCP server.\
    Refer to the [MCP documentation](/docs/AI-Agent-Toolkit/MCP/Overview) for environment-specific setup.
  </Step>

  <Step title="Call the `messaging.send` tool">
    Once configured, use your assistant or client to trigger a notification using the `messaging.send` method — no workflow setup required.
  </Step>

  <Step title="Track message status">
    Use tools like `messaging.getStatus` or the `/message-status/{id}` endpoint to monitor delivery.
  </Step>
</Steps>

### Using AI Agent Toolkit

If you are using AI Agent toolkit to send a notification quickly, follow these steps:

<Steps>
  <Step title="Install the Agent Toolkit">
    Install the SDK using your preferred package manager:\
    `npm install @trysiren/agent-toolkit`\
    or\
    `yarn add @trysiren/agent-toolkit`
  </Step>

  <Step title="Initialize the toolkit with your API key">
    Import `SirenToolkit` and pass your API key during initialization.\
    You can optionally configure the messaging tool permissions.
  </Step>

  <Step title="Expose tools to your AI framework">
    Use the `getTools()` method to expose Siren tools (like `send_message`) to frameworks like OpenAI, LangChain, or Vercel AI SDK.
  </Step>

  <Step title="Trigger messages using `send_message` tool">
    The agent can now use function calls to send notifications on supported channel,— just like an API or MCP request.
  </Step>

  <Step title="Monitor delivery with `get_message_status` or logs">
    Use status-checking tools within the agent environment, or fallback to Siren’s tracking endpoints and logs.
  </Step>
</Steps>

Refer to the [AI Agent Toolkit documentation](/docs/AI-Agent-Toolkit/AI%20Agent%20Toolkit) for full implementation details.

### Using SDK

If you are using the Siren SDK to send a notification quickly, follow these steps:

<Steps>
  <Step title="Install the SDK">
    ```python theme={null}
    pip install trysiren
    ```
  </Step>

  <Step title="Initialize the client">
    ```python theme={null}
    from siren import SirenClient
    client = SirenClient()  # Uses SIREN_API_KEY from environment
    ```
  </Step>

  <Step title="Send a message">
    ```python theme={null}
    client.message.send(
        recipient_value="user@example.com",
        channel="EMAIL",
        template_name="welcome_template",
        template_variables={
            "firstName": "John",
            "offerCode": "ABCD123"
        }
    )
    ```
  </Step>

  <Step title="(Optional) Track delivery status">
    ```python theme={null}
    client.message.get_status("notificationId")
    ```
  </Step>
</Steps>

<Info>
  This example demonstrates usage with the Python SDK. Siren also provides a TypeScript SDK, and the same procedures can be followed using TypeScript as well. For details on the TypeScript SDK and complete SDK usage, refer to the [SDK Documentation](/docs/SDK/backend/python-sdk).
</Info>

For more complex orchestration, you can utilise the workflow editor and start designing your own [notification workflow](/docs/Workflow/CreatingWorkflow).