How to Use the MagicBell MCP in Vercel AI SDK

Q: Can I stream MagicBell broadcast creation logs live with Vercel AI SDK?

Yes. When your agent calls createbroadcast, the Vercel AI SDK streams the resulting payload status chunk-by-chunk directly to your React components, avoiding UI lag.

Q: Can I use Vercel AI SDK to filter notifications retrieved from MagicBell?

Absolutely. You can instruct your agent to call listbroadcasts and then use the SDK's language model capabilities to filter, sort, or summarize the notification history based on user requests.

Ship real-time notification streams directly into your Next.js frontend using MagicBell and Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect MagicBell to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger instant alerts in your UI

The `create_broadcast` tool lets your AI client broadcast notifications across multiple channels instantly. Instead of waiting for a backend queue to finish processing, your Vercel AI SDK setup triggers the broadcast directly during a live chat or automated agent run. This means your users see notification confirmations pop up in their feed immediately. The streaming interface handles the state updates without forcing a full page reload or showing a generic loading spinner.

Stream broadcast history live with this MCP Server

The `list_broadcasts` tool fetches the history of sent alerts directly into your streaming UI context. Your AI client pulls the log of recent broadcasts to show users exactly what messages went out and when. By feeding this data straight into the Vercel AI SDK, the text streams onto the screen as it arrives. Developers get a clean way to show live activity logs without building custom polling mechanisms.

Inspect specific notification runs

The `get_broadcast` tool retrieves the exact payload, status, and recipient details for a single notification ID. Your agent uses this tool to debug delivery failures or check dispatch details on the fly. This MCP Server integration lets you render these details inside custom React components instantly. If a user asks why they missed an alert, the agent pulls the data and renders the status live.

Setup guide

Set up MagicBell MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all MagicBell tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent MagicBell transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You do not need to hardcode keys in your frontend. Vinkius manages the authentication securely on the backend, giving your Vercel AI SDK client a single secure endpoint token to run all tools.

Yes. When your agent calls `create_broadcast`, the Vercel AI SDK streams the resulting payload status chunk-by-chunk directly to your React components, avoiding UI lag.

The server offloads the heavy lifting to MagicBell's infrastructure. Your AI client simply triggers the event, and the external API manages multi-channel delivery to thousands of users.

Absolutely. You can instruct your agent to call `list_broadcasts` and then use the SDK's language model capabilities to filter, sort, or summarize the notification history based on user requests.

All transmission occurs over TLS-encrypted connections directly to the API. The Vinkius MCP platform runs the server in an ephemeral V8 sandbox, meaning recipient emails and notification payloads are never cached or stored on our servers.

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