How to Use the Gallabox MCP in Mastra AI

Q: How do I install the Gallabox integration for Mastra AI?

You install @mastra/mcp and instantiate a new client with your endpoint URL. Mastra automatically detects if the connection uses Streamable HTTP or SSE. Spread the resulting tools into your agent configuration.

Q: Does the MCP Server support human-in-the-loop approval workflows?

It does. You can enable requireToolApproval for destructive actions like sending broadcast templates. The workflow pauses execution until a human reviews the message and clicks approve.

Q: How do I load tools into my agent configuration?

Call mcpClient.listTools() and pass the array directly into your agent's tools property. The agent immediately understands the schema for every WhatsApp operation available.

Construct resilient WhatsApp messaging workflows in Mastra AI with the Gallabox 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 Gallabox MCP to Mastra AI

Create your Vinkius account to connect Gallabox 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 Gallabox with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build conditional MCP Server workflows

The `verify_api_connection` tool checks your WhatsApp Business API status before executing large broadcast runs. Mastra AI uses this to build conditional logic. If the connection fails, the workflow pauses and triggers an exponential backoff sequence. Once the connection clears, the agent calls `send_whatsapp_template`. You map out exact failure paths. If Meta rejects a template due to rate limits, Mastra catches the error and alerts an administrator instead of dropping the task silently.

Handle chat escalations

The `get_chat_details` tool extracts thread metadata, including current assignee and status. Your Mastra AI agent reads this state to determine if a conversation requires human intervention. It checks the timestamps and sentiment of recent replies. When an escalation triggers, the agent runs `list_support_teams`. It finds the available human agents in Gallabox and routes the thread ID to them. You define these branching rules directly in your workflow engine.

Sync contacts and manage state

The `list_whatsapp_contacts` tool dumps bulk contact records from your WhatsApp channel. Your workflow ingests this list and loops through individual records using `get_contact_details`. This builds a localized cache of customer data for your internal systems. You manage the entire synchronization process through the MCP protocol. Mastra handles the asynchronous execution. If a lookup times out, the built-in retry mechanism attempts the fetch again without crashing the entire run.

Setup guide

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

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

const result = await agent.generate(
  "List recent Gallabox 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 Gallabox. 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 Gallabox 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 Gallabox MCP in Mastra AI

You install `@mastra/mcp` and instantiate a new client with your endpoint URL. Mastra automatically detects if the connection uses Streamable HTTP or SSE. Spread the resulting tools into your agent configuration.

Yes. You configure exponential backoff in your Mastra workflow. If a `send_whatsapp_text` call fails due to API limits, the engine waits and retries the exact payload automatically.

It does. You can enable `requireToolApproval` for destructive actions like sending broadcast templates. The workflow pauses execution until a human reviews the message and clicks approve.

Call `mcpClient.listTools()` and pass the array directly into your agent's tools property. The agent immediately understands the schema for every WhatsApp operation available.

All chat metadata and contact profiles route through an ephemeral V8 Isolate. The system drops the connection and wipes the memory state after the workflow step completes. Zero customer data writes to disk.

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