How to Use the Wati MCP in Mastra AI

Q: How do I ensure data integrity when checking Wati contacts with Mastra AI?

The MCP Server manages the state. When you call listwhatsappcontacts, Mastra AI holds that list as an output variable for subsequent steps, ensuring your next tool (like sending a message) uses the most current contact dataset.

Q: Can I monitor templates with Wati using Mastra AI?

Yes. You can check listwhatsapptemplates to see which are pending approval, and then build a workflow that only allows sending if the template status is 'Approved.' This makes your automation safe.

Q: If I need to audit chat history, how does Wati work with Mastra AI?

You use getwhatsappchathistory within your workflow. You can then conditionally send an alert or log the retrieved conversation data based on specific keywords found in the messages.

Build reliable, multi-step WhatsApp automation workflows with Mastra AI and Wati MCP Server.

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 Mastra AI

Create your Vinkius account to connect Wati to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Handling Failed Messaging Workflows in Mastra AI

You can build complex processes around message sending. For instance, your workflow attempts to `send_template_message`. If the API call fails—say, due to a temporary network issue—Mastra AI automatically retries it with exponential backoff. This built-in failure handling is crucial for production systems. It means you don't need custom retry logic; the platform manages the complexity so your automation succeeds reliably.

Conditional WhatsApp Operations on Mastra AI

Mastra AI allows conditional branching in your workflow engine. You can sequence tasks like this: check if the user is a contact using `get_whatsapp_contact_details`. If they aren't, then trigger a manual review step; otherwise, proceed to send a message. This logic ensures that every action taken by the MCP Server—like calling `send_session_message`—is based on defined business rules, not just simple sequencing.

Managing Wati Contacts and Campaigns with Mastra AI

Need to manage a large batch operation? You can start by listing all contacts using `list_whatsapp_contacts`, then checking the campaign status via `list_broadcast_campaigns`. This whole sequence runs in one reliable, multi-step workflow. Mastra AI handles the state between these tool calls. It remembers the contact list from step one when it gets to step two, ensuring data integrity across your entire automation.

Setup guide

Set up Wati MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Wati tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "wati-mcp-client",
  servers: {
    "wati-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Wati Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Wati tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Wati transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI detects the failure and executes its retry logic. It automatically attempts to resend the message, increasing the wait time between tries until success or until the workflow hits a defined limit.

The MCP Server manages the state. When you call `list_whatsapp_contacts`, Mastra AI holds that list as an output variable for subsequent steps, ensuring your next tool (like sending a message) uses the most current contact dataset.

Yes. You can check `list_whatsapp_templates` to see which are pending approval, and then build a workflow that only allows sending if the template status is 'Approved.' This makes your automation safe.

This server interacts with WhatsApp contact details, message templates, and broadcast campaign metadata. The primary data type being managed is the Template structure itself.

You use `get_whatsapp_chat_history` within your workflow. You can then conditionally send an alert or log the retrieved conversation data based on specific keywords found in the messages.

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