How to Use the 360dialog MCP in Mastra AI

Q: How do I load 360dialog tools into my Mastra AI agent?

Install @mastra/mcp and instantiate MCPClient with your Vinkius URL. Mastra auto-detects the Streamable HTTP transport. Call listTools() and spread them into your agent's tool array.

Q: Can Mastra AI require human approval before sending 360dialog messages?

You control the execution flow. Wrap sendmessage or sendtemplatemessage with Mastra's requireToolApproval flag. The workflow will pause and wait for a manager to hit approve before pushing the text to WhatsApp.

Q: How do I handle media attachments in these workflows?

You chain the steps. Have one step use uploadmedia to stage the file. Pass the resulting media ID down the workflow to the sendmediamessage tool for final delivery.

Q: Does the MCP integration support checking message templates?

Yes. Your workflow can query listtemplates to find approved layouts. If a required template is missing, the agent can halt the sequence and alert your marketing team.

Build resilient WhatsApp workflows in Mastra AI using the 360dialog MCP Server to handle automated messaging and retries.

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 Mastra AI

Create your Vinkius account to connect 360dialog 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 360dialog with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate fallback logic for failed WhatsApp messages

Networks drop requests and rate limits hit when you least expect them. You cannot afford to lose a critical customer notification just because the initial request timed out. Building this inside Mastra AI gives you automatic exponential backoff. If `send_message` fails due to a temporary glitch, your workflow catches the error and retries automatically. You can even branch the logic to trigger `send_template_message` with a different language code if the first attempt bounces.

Validate numbers before executing campaign steps

Blasting out thousands of updates requires clean data. Sending payloads to invalid numbers drains your budget and flags your account for spam. Insert `check_contacts` as the first node in your Mastra workflow. The agent verifies the WhatsApp status of every number. Valid numbers proceed to the `send_media_message` step, while invalid ones get routed to an admin notification queue.

Configure MCP Server webhooks dynamically during deployment

Hardcoding callback URLs into your codebase makes migrating between environments a massive headache. Your staging and production workflows need different endpoints. Let the system handle the configuration on the fly. Your deployment workflow can call `set_webhook` to point the official API at your new Mastra instance. You can also run `check_360dialog_status` to ensure everything connected properly before taking the new workflow live.

Setup guide

Set up 360dialog 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 360dialog 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: "360dialog-mcp-client",
  servers: {
    "360dialog-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "360dialog Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to 360dialog tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent 360dialog 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 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 Mastra AI

Install `@mastra/mcp` and instantiate `MCPClient` with your Vinkius URL. Mastra auto-detects the Streamable HTTP transport. Call `listTools()` and spread them into your agent's tool array.

You control the execution flow. Wrap `send_message` or `send_template_message` with Mastra's `requireToolApproval` flag. The workflow will pause and wait for a manager to hit approve before pushing the text to WhatsApp.

You chain the steps. Have one step use `upload_media` to stage the file. Pass the resulting media ID down the workflow to the `send_media_message` tool for final delivery.

Yes. Your workflow can query `list_templates` to find approved layouts. If a required template is missing, the agent can halt the sequence and alert your marketing team.

The ephemeral architecture means Vinkius retains zero state between workflow executions. The images you upload and the template layouts you fetch pass through a zero-trust proxy directly to the provider. Nothing gets cached on our infrastructure.

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