How to Use the Gupshup Messaging MCP in Vercel AI SDK

Q: How do I connect the Gupshup Messaging MCP Server to my Vercel AI SDK project?

Install @ai-sdk/mcp and call createMCPClient using the HTTP transport pointing to your Vinkius endpoint. You then pass the tools directly into generateText or streamText and remember to call close() when the session ends.

Q: Can my Vercel AI SDK agent handle WhatsApp media attachments through Gupshup Messaging?

Yes, the agent calls sendmediamessage with your target phone number and the media URL. It handles PDFs, audio, images, and video, feeding the Gupshup API response directly back to your React components.

Q: How does Gupshup Messaging handle template variables inside Vercel AI SDK edge functions?

You run gettemplateinfo to retrieve the schema, then pass the variables array to sendtemplatemessage. The edge function processes the payload instantly, avoiding cold starts.

Build real-time WhatsApp interfaces where your AI-driven Next.js app sends messages instantly using the 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 Gupshup Messaging MCP to Vercel AI SDK

Create your Vinkius account to connect Gupshup Messaging 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 Gupshup Messaging with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream WhatsApp text and media directly from Vercel AI SDK

This Gupshup Messaging MCP Server exposes `send_text_message` and `send_media_message` to dispatch WhatsApp alerts directly inside your Vercel AI SDK streaming loops. Instead of waiting for a backend queue to finish, your Next.js application triggers the Gupshup API instantly as the user chats, rendering live delivery states in the frontend. You pass the media URLs or raw text payloads directly into the tool call. The Vercel AI SDK UI components catch the execution state, meaning your users see the document or image upload status on their screens without annoying page refreshes.

Trigger interactive WhatsApp buttons on the edge

The `send_interactive_message` tool lets your edge functions send quick-reply buttons and lists to users without spinning up heavy server environments. Because the Vercel AI SDK MCP client runs on lightweight edge runtimes, your agent evaluates user intent and fires off structured WhatsApp options in milliseconds. You define up to three buttons in a simple JSON array. Your conversational agent determines the best response pathway, calls this tool, and immediately updates the live chat UI with the sent options.

Dispatch pre-approved templates with zero loading lag

The `send_template_message` and `get_template_info` tools let your Vercel AI SDK setup inspect and send highly formatted WhatsApp template messages to users. Your agent pulls the exact language codes and variable parameters from your database, matches them against Gupshup's requirements, and fires them off. This stops your UI from freezing while waiting for external API handshakes. The streaming client processes the template variables asynchronously, keeping your Next.js dashboard fast and responsive.

Setup guide

Set up Gupshup Messaging 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 Gupshup Messaging 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 Gupshup Messaging 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 Gupshup. 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 Gupshup Messaging 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 Gupshup Messaging MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and call `createMCPClient` using the HTTP transport pointing to your Vinkius endpoint. You then pass the tools directly into `generateText` or `streamText` and remember to call `close()` when the session ends.

Yes, the agent calls `send_media_message` with your target phone number and the media URL. It handles PDFs, audio, images, and video, feeding the Gupshup API response directly back to your React components.

You run `get_template_info` to retrieve the schema, then pass the variables array to `send_template_message`. The edge function processes the payload instantly, avoiding cold starts.

The button click triggers a WhatsApp webhook. You will need to route that webhook back to your Next.js API route to update the Vercel AI SDK chat state.

Your recipient phone numbers, message payloads, and template parameters are processed inside an ephemeral V8 sandbox. Vinkius never logs the body of your WhatsApp messages, keeping your customer data 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