How to Use the 360dialog MCP in Vercel AI SDK

Q: How do I connect 360dialog to the Vercel AI SDK?

Install @ai-sdk/mcp and initialize with createMCPClient. Pass the Vinkius endpoint URL using the HTTP transport type. Then call mcpClient.tools() and feed the result into your text generation loop.

Q: Can the Vercel AI SDK stream 360dialog delivery receipts?

Yes, if you configure your endpoints properly. Use setwebhook to point the event payloads at your Next.js API route. Your app can then push those updates to the client via Server-Sent Events.

Q: What happens if a WhatsApp message fails to send?

The sendmessage tool returns the error directly to your agent. You can catch this in your generation logic and prompt the user to check the formatting of the international phone number.

Build live WhatsApp messaging features into your React apps using the 360dialog MCP Server 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 360dialog MCP to Vercel AI SDK

Create your Vinkius account to connect 360dialog 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 360dialog with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream WhatsApp template fetching via Vercel AI SDK

Your Next.js users hate staring at loading spinners while waiting for message templates to load. Hooking this MCP Server into `streamText` means your frontend renders the available formats as fast as the AI reads them. You call `list_templates` and the UI populates instantly. Fetching specific details works exactly the same way. When a user selects a layout, the `get_template` tool pulls the language codes and variables right into your component state. No polling the backend required.

Send rich media messages straight from the browser

Text alerts only get you so far when dealing with customer support. You need a way to push images and documents directly to WhatsApp without writing custom API routes for every file type. Pass the file URL to `send_media_message` right inside your edge function. If you need to host the file first, `upload_media` handles the staging before the dispatch fires. The Vercel AI SDK streams the delivery confirmation back to your user's dashboard in milliseconds.

Validate contacts and check API status instantly

Firing messages into the void wastes money and ruins your delivery metrics. You need to know if a phone number actually has an active WhatsApp account before you try hitting it. The `check_contacts` tool verifies the recipient number in international format on the fly. If something breaks, your AI client can run `check_360dialog_status` to diagnose connectivity issues and display a clean error message in the UI instead of crashing the app.

Setup guide

Set up 360dialog 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 360dialog 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 360dialog 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 360dialog. 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 360dialog 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 360dialog MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize with `createMCPClient`. Pass the Vinkius endpoint URL using the HTTP transport type. Then call `mcpClient.tools()` and feed the result into your text generation loop.

Yes, if you configure your endpoints properly. Use `set_webhook` to point the event payloads at your Next.js API route. Your app can then push those updates to the client via Server-Sent Events.

It works perfectly. The MCP protocol uses standard HTTP requests, meaning you don't need Node.js primitives. Just remember to call `mcpClient.close()` when your edge function finishes.

The `send_message` tool returns the error directly to your agent. You can catch this in your generation logic and prompt the user to check the formatting of the international phone number.

Vinkius runs the server inside a V8 Isolate Sandbox that destroys itself after execution. Your raw customer phone numbers and message contents never sit in persistent storage. The endpoint passes the payload straight to the official API and vanishes.

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