How to Use the BoxLock MCP in OpenAI Agents SDK
Secure package deliveries by connecting BoxLock to your OpenAI Agents SDK project for automated, verified access control.
Works with every AI agent you already use
…and any MCP-compatible client
Connect BoxLock MCP to OpenAI Agents SDK
Create your Vinkius account to connect BoxLock 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.
Remote Access Control with OpenAI Agents SDK
Your agent triggers `press_to_open` to remotely unlock your hardware. It handles the physical verification of delivery carriers in real-time. This MCP Server provides the interface for your agent to execute commands safely. You avoid manual oversight while maintaining strict entry logs.
Audit Activity Logs via OpenAI Agents SDK
Call `list_activities` to pull the precise history of every package drop-off. Your agent parses these logs to detect patterns or missed deliveries. You'll get an immediate view of site status without digging through external dashboards. It turns raw log data into actionable insights for your agent system.
Manage Hardware Inventory with OpenAI Agents SDK
Use `list_locks` and `list_locations` to map your entire physical infrastructure. Your agent keeps an updated state of where every device resides. This setup ensures your agent knows exactly which hardware to target for a specific command. It prevents errors caused by outdated local records.
Set up BoxLock MCP in OpenAI Agents SDK
Prerequisites
- Python 3.10+ installed
-
openai-agentspackage (pip install openai-agents) - Active Vinkius subscription with a valid endpoint token
- 1
Install the SDK
Run
pip install openai-agentsto install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed. - 2
Connect via SSE transport
Use
MCPServerSsewith your Vinkius endpoint URL. Replace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. The SDK auto-discovers all BoxLock tools at runtime. - 3
Create your Agent
Pass the MCP to
Agent(mcp_servers=[server]). The agent receives BoxLock tools as native definitions — JSON schemas resolve automatically. - 4
Run the agent
Call
Runner.run(agent, prompt)to execute. The agent invokes the appropriate BoxLock tools and returns structured results. Copy the full example on the right to get started.
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="BoxLock Agent",
instructions="You have access to BoxLock tools.",
mcp_servers=[server],
)
result = await Runner.run(agent, "List recent transactions")
print(result.final_output)
asyncio.run(main()) Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by BoxLock. 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.
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 BoxLock MCP in OpenAI Agents SDK
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the BoxLock MCP today
We host it, we monitor it, we maintain it. You just paste one token.