How to Use the MailboxPower MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent send physical gifts via MailboxPower?

Yes. The agent calls sendshipment to dispatch physical items. You should configure strict guardrails to prevent accidental API calls that incur real-world costs.

Q: Does MailboxPower work with OpenAI Agents SDK multi-agent handoffs?

It works perfectly. One agent formats addresses using createcontact, then hands off the payload to a fulfillment agent that triggers sendshipment. The OpenAI dashboard logs the entire chain.

Q: How do I list available MailboxPower campaigns using OpenAI Agents SDK?

Your agent executes listautomations to read the active campaigns. It then routes users into those sequences based on your custom logic. Set cacheToolsList to true to speed up the discovery phase.

Automate physical mail directly from your OpenAI Agents SDK production workflows with this 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 MailboxPower MCP to OpenAI Agents SDK

Create your Vinkius account to connect MailboxPower to OpenAI Agents 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 MailboxPower with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger physical mail via MCP Server

`send_shipment` dispatches physical gifts and greeting cards directly from your code. You pass the recipient details to your agent, and it handles the fulfillment API call. The OpenAI dashboard tracks every outbound package request alongside your standard digital logs. Guardrails prevent run-away spending. You set strict budget rules in your agent definition before it executes the shipment. If an agent tries to blast expensive gifts to an unverified list, the framework stops the execution immediately.

Manage your recipient database

`create_contact` and `get_contact` manage the recipient database. The MCP connection lets your agent pull existing addresses or add new ones based on conversation context. Handoffs let a specialized data-cleaning agent format the addresses before the fulfillment agent takes over the transaction. You keep the CRM in sync without manual data entry. `list_contacts` pulls down the current roster for batch processing. The agent validates the formatting, ensuring physical mail actually reaches the intended desks.

Execute sequential direct mail campaigns

`add_contact_to_automation` drops a user into a predefined MailboxPower sequence. Your agent reads the available campaigns using `list_automations` and assigns the prospect to the right track. This connects digital intent directly to analog delivery. Grouping works the exact same way. The agent fires `create_group` for a specific event, then uses `add_contact_to_group` to build the list. You get a fully automated pipeline for physical event follow-ups.

Setup guide

Set up MailboxPower MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all MailboxPower tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives MailboxPower tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MailboxPower tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="MailboxPower Agent",
            instructions="You have access to MailboxPower tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Setup requires pip installing openai-agents. You create an MCPServerStreamableHttp instance with your Vinkius URL and pass it to the Agent constructor. The framework auto-discovers all nine fulfillment tools.

Yes. The agent calls `send_shipment` to dispatch physical items. You should configure strict guardrails to prevent accidental API calls that incur real-world costs.

It works perfectly. One agent formats addresses using `create_contact`, then hands off the payload to a fulfillment agent that triggers `send_shipment`. The OpenAI dashboard logs the entire chain.

Your agent executes `list_automations` to read the active campaigns. It then routes users into those sequences based on your custom logic. Set cacheToolsList to true to speed up the discovery phase.

MailboxPower processes physical shipping addresses and contact names. Vinkius isolates this data inside an ephemeral V8 sandbox. The execution context vanishes the moment the API call finishes.

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