How to Use the MagicBell MCP in OpenAI Agents SDK

Q: How do I debug a failed MagicBell broadcast with the OpenAI Agents SDK?

Use the OpenAI dashboard. The tracing will show the exact createbroadcast call with its parameters. You can then use the getbroadcast tool with the broadcast ID to check its status directly with MagicBell.

Build production-ready agents that manage MagicBell notifications with the OpenAI Agents SDK and its built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MagicBell MCP to OpenAI Agents SDK

Create your Vinkius account to connect MagicBell to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup MagicBell with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send Broadcasts Safely

The `create_broadcast` tool lets your agent send multi-channel notifications through MagicBell. Hook it into your monitoring system, and your agent can alert your team about system outages or critical events. Here's the thing: the OpenAI Agents SDK wraps this action with guardrails. You can define rules to prevent the agent from sending duplicate alerts or exceeding rate limits, which is critical for a production system. It's not just about sending a message; it's about sending the right one, once.

Debug Notifications with Full Tracing

Use the `list_broadcasts` and `get_broadcast` tools to give your agent a history of all notifications. Your support agent can ask, "What was the last alert sent for server-db-01?" and get a direct answer. Every call your agent makes is traced in the OpenAI dashboard. If a broadcast was sent incorrectly, you can see the exact agent state and reasoning that led to the `create_broadcast` call. No more guesswork.

Manage Alerts with Your MCP Server

This MCP server exposes MagicBell's core broadcast functions without any extra layers. Your agent gets direct access to what it needs to manage alerts, and nothing it doesn't. Because the OpenAI Agents SDK auto-discovers tools, setup is minimal. Point it at the server URL, and your agent is immediately equipped to `create_broadcast`, `get_broadcast`, and `list_broadcasts`.

Setup guide

Set up MagicBell MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all MagicBell tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives MagicBell tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MagicBell tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="MagicBell Agent",
            instructions="You have access to MagicBell tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by MagicBell. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect MagicBell now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about MagicBell MCP in OpenAI Agents SDK

The SDK will catch the API error from the MagicBell MCP server. You can program your agent's logic to handle these exceptions, like retrying the broadcast or logging the failure for review.

Yes. While the SDK discovers all tools by default, you can configure the agent to only use a specific subset. For instance, you could allow `get_broadcast` for a read-only support agent but restrict `create_broadcast`.

Yes. Your key is stored in the managed Vinkius MCP server, not in your agent's code. The agent authenticates to the server using a Vinkius token, keeping your MagicBell credentials isolated and secure.

Use the OpenAI dashboard. The tracing will show the exact `create_broadcast` call with its parameters. You can then use the `get_broadcast` tool with the broadcast ID to check its status directly with MagicBell.

The server only handles notification data: recipient identifiers, message content, and broadcast metadata. It doesn't access any other part of your MagicBell account. All traffic is encrypted, and the Vinkius sandbox environment ensures your data remains isolated.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript