How to Use the Arbox MCP in OpenAI Agents SDK

Q: How do I connect the Arbox MCP server to my OpenAI Agents SDK project?

You'll use MCPServerStreamableHttp and pass your Vinkius endpoint URL. Just add the server instance to the mcpservers list when you create your agent. The SDK handles tool discovery automatically.

Q: Can my OpenAI Agent get a list of all sales leads from Arbox?

Yes, that's what the listleads tool is for. Your agent can call it to get a list of your current sales leads directly from your Arbox pipeline. You can then have the agent analyze or summarize the data.

Q: What's the best way to find a specific member in Arbox using the OpenAI Agents SDK?

Use the searchmembers tool. It's more powerful than a simple lookup because it returns the member's profile, attendance, and engagement score. Your OpenAI Agent can use that rich data to make smarter decisions.

Give your OpenAI Agent secure access to manage your Arbox studio, with guardrails to validate every action.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arbox MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Your Sales Pipeline & Members

Build an agent that tracks your studio's health. You can ask it to `list_leads` to check the sales pipeline or use `search_members` to find a specific person and see their engagement score. The OpenAI Agent SDK discovers these tools automatically, so you just connect the MCP server and start giving commands. This isn't just for one-off queries. You can create specialized agents, one for sales and one for member retention, that hand off tasks. The built-in tracing lets you see exactly how your agent decided to pull a member's payment history with `list_payments` or check their membership status with `get_member`.

Run Day-to-Day Studio Operations

This MCP Server puts your Arbox studio's core operations into your agent's hands. Ask for the upcoming class schedule with `list_schedule` or get a list of available trainers using `list_coaches`. Your agent gets structured data back, ready for any follow-up task. Because the OpenAI Agents SDK has guardrails, you can let your agent act on this data without constant supervision. It won't accidentally call the wrong tool or pass bad data. You can even set `cacheToolsList=True` for faster responses when your agent repeatedly checks things like product inventory with `list_products`.

Build a Production Arbox Agent with the OpenAI SDK

Go from a simple script to a real product. The OpenAI Agent SDK is built for production, and this Arbox server gives it the tools it needs. Your agent can handle complex requests that require multiple steps, like finding a member with `search_members` and then pulling their full profile with `get_member`. The `async with` context manager ensures clean connections and shutdowns. All agent actions are validated before they run, preventing mistakes. This setup gives you a reliable way to connect your Python application directly to your Arbox business intelligence data.

Setup guide

Set up Arbox 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 Arbox tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Arbox 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="Arbox Agent",
            instructions="You have access to Arbox 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 Arbox. 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 Arbox 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 Arbox MCP in OpenAI Agents SDK

You'll use `MCPServerStreamableHttp` and pass your Vinkius endpoint URL. Just add the server instance to the `mcp_servers` list when you create your agent. The SDK handles tool discovery automatically.

Yes, that's what the `list_leads` tool is for. Your agent can call it to get a list of your current sales leads directly from your Arbox pipeline. You can then have the agent analyze or summarize the data.

Use the `search_members` tool. It's more powerful than a simple lookup because it returns the member's profile, attendance, and engagement score. Your OpenAI Agent can use that rich data to make smarter decisions.

The SDK itself focuses on auto-discovery, but you can control this in your agent's logic. You'd build a specialized agent and programmatically restrict its available actions to a subset of the Arbox tools you want it to access.

The server only touches your Arbox studio data: member profiles, schedules, payments, and leads. Your Vinkius endpoint token is the only credential needed. All requests are made over HTTPS through an ephemeral, sandboxed environment that's destroyed after each session.

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