How to Use the BoxHero MCP in OpenAI Agents SDK

Q: Can I trace tool calls made by my agent?

Yes. Every call to tools like getaccountinfo or listlocations appears inside your OpenAI developer dashboard. You see the exact input parameters and the JSON response returned by the server.

Run production-grade inventory agents that modify BoxHero stock using the OpenAI Agents SDK and guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BoxHero MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe inventory updates with OpenAI Agents SDK

The `create_transaction` tool logs stock movements directly inside your BoxHero account. Your Python agent executes this tool only after passing your SDK-defined validation guardrails, preventing accidental stock double-entry in production. This MCP setup lets your agent inspect current stock levels using `list_items` before it triggers any changes. You track the entire execution path and tool calls live on your OpenAI developer dashboard.

Multi-agent handoffs for warehouse routing

The `list_locations` tool retrieves your physical storage zones so specialized routing agents can coordinate where items go. One agent queries the locations, while another handles the actual updates via `update_item`. Because the OpenAI Agents SDK supports clean handoffs, you do not have to write complex logic to switch contexts. The routing agent hands off the payload to the execution agent, which then runs `create_item` to initialize new stock arrivals.

Automated stock verification and audits

The `list_transactions` tool pulls historical stock logs so your agent can audit past changes without manual export steps. Your agent compares actual quantities against your database records, flagging discrepancies instantly. By connecting this MCP Server to your production pipeline, you get real-time auditing. The agent uses `get_item` to inspect specific SKU details and updates the catalog using `update_item` when it detects mismatched data.

Setup guide

Set up BoxHero 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 BoxHero tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and spin up the MCPServerStreamableHttp client using your Vinkius URL. Pass this server to your Agent constructor so it instantly discovers tools like `list_items` and `create_transaction`.

Yes. You control tool access by defining strict guardrails in your Python code before the agent calls tools like `delete_item` or `update_item`. The SDK validates the arguments against your schema before sending the request.

The SDK relies on Vinkius to queue and manage the underlying HTTP requests to the BoxHero API. If your agent runs `list_items` in a loop, Vinkius handles the request throttling to keep your connection stable.

Yes. Every call to tools like `get_account_info` or `list_locations` appears inside your OpenAI developer dashboard. You see the exact input parameters and the JSON response returned by the server.

All inventory items, transaction histories, and storage locations stay secure inside V8 isolate sandboxes. Vinkius processes your requests ephemerally, meaning your raw credentials and stock data are never written to persistent 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