How to Use the Wati MCP in Vercel AI SDK

Q: How do I verify Wati connectivity using my AI SDK?

You run the checkwatistatus tool. This immediately tells your agent if the server can talk to WhatsApp, so you don't waste time sending messages when there's an outage.

Q: Does the Wati MCP Server support sending different message types with ai-sdk?

Yep. It gives you three main options: simple chat updates (sendsessionmessage), pre-approved forms using templates (sendtemplatemessage), and media attachments (sendmediamessage). Your agent picks the best one.

Q: Can I list all contacts available through Wati with my AI SDK?

Absolutely. You use the listcontacts tool to get a full roster of contacts managed by Wati. This data is then streamed back to your client so you can display it in real-time.

Real-time WhatsApp messaging for your AI SDK UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wati MCP to Vercel AI SDK

Create your Vinkius account to connect Wati 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 Wati with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Real-Time Messaging to the User.

When you use this MCP Server, tool results stream directly into your user interface. You can show contacts appearing live or message status updates instantly. This is critical for building real-time chat experiences. Instead of showing a 'loading' state, users see data—like the result of `list_messages` or contact details from `get_contact`—appear as they stream in.

Manage Contacts and Templates via Your AI SDK.

Your agent can manage entire communication cycles. You'll use tools like `add_contact` to onboard a new user, or `update_contact` if their details change. Before sending anything, your client can check available message structures using `list_templates`. This lets you ensure the messaging process remains clean and accurate for the end user.

Send Structured Messages with MCP Server.

The server handles multiple outbound formats. You'll send basic updates using `send_session_message`, or structured campaigns via `send_template_message`. It also supports rich media, so you can use `send_media_message` to attach images directly in the UI. For larger outreach, you can call `list_broadcasts` to see what large-scale messages are scheduled.

Setup guide

Set up Wati 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 Wati 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 Wati 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 Wati. 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 Wati 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 Wati MCP in Vercel AI SDK

You run the `check_wati_status` tool. This immediately tells your agent if the server can talk to WhatsApp, so you don't waste time sending messages when there's an outage.

This MCP Server handles contact details, message history, and template identifiers. Specifically, it manages `contact` attributes, which are used in tools like `get_contact` and `update_contact`.

Yep. It gives you three main options: simple chat updates (`send_session_message`), pre-approved forms using templates (`send_template_message`), and media attachments (`send_media_message`). Your agent picks the best one.

Absolutely. You use the `list_contacts` tool to get a full roster of contacts managed by Wati. This data is then streamed back to your client so you can display it in real-time.

The server deals with contact and message data. It specifically touches `contact` attributes, including names and phone numbers. You'll need to handle that PII securely within your own application logic.

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