How to Use the MailboxPower MCP in Mastra AI

Q: How do I require human approval before MailboxPower sends a gift in Mastra AI?

Set the requireToolApproval property to true on the sendshipment tool within your Mastra agent configuration. This halts the workflow and alerts an admin before any physical card is printed or shipped.

Build resilient physical gifting workflows using Mastra AI and automated retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MailboxPower MCP to Mastra AI

Create your Vinkius account to connect MailboxPower 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 MailboxPower with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient gifting via Mastra AI and this MCP Server

Sending physical items costs real money, which means you cannot afford failed API calls or lost addresses. Mastra's built-in workflow engine lets you write conditional logic around `send_shipment` to handle delivery errors. If a print job fails, the agent uses exponential backoff to retry the request. You can set up human-in-the-loop approval before any high-value gift actually leaves the warehouse.

Multi-step contact management workflows

Keep your recipient database pristine by chaining multiple actions together in a single, resilient Mastra workflow. The agent starts by running `get_contact` to check if a recipient exists in your records. If the contact is missing, the system runs `create_contact` and immediately follows up with `add_contact_to_group` to categorize them. This prevents duplicate profiles and ensures every physical parcel goes to the right home.

Automate direct mail campaigns conditionally

You can build complex branching logic that triggers physical mailers based on customer behavior. The agent uses `list_automations` to check which campaigns are currently active for a specific user segment. Once verified, it calls `add_contact_to_automation` to drop the user into a high-touch direct mail sequence. This MCP Server handles the execution steps, ensuring the physical mail triggers only when specific customer milestones are met.

Setup guide

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

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

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

Set the requireToolApproval property to true on the send_shipment tool within your Mastra agent configuration. This halts the workflow and alerts an admin before any physical card is printed or shipped.

Yes, Mastra's workflow engine includes built-in retry mechanisms with backoff. If list_groups or list_contacts hits a rate limit, the client automatically pauses and retries without crashing your application.

Initialize the MCP client with the server's endpoint, call listTools(), and spread those tools directly into your agent's tool array. Your agent can then run create_group or add_contact_to_group autonomously.

It does, handling both Streamable HTTP and SSE transports for this MCP Server out of the box. You just point the client to the Vinkius URL, and the framework configures the communication channel automatically.

Mastra processes the contact details in memory during the execution of create_contact and does not persist them. All recipient names and mailing addresses are sent directly through the Vinkius proxy to the secure API, ensuring no customer data leaks into your application logs.

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