How to Use the Booqable MCP in OpenAI Agents SDK

Q: How do I configure Booqable tool discovery in the OpenAI Agents SDK?

Install openai-agents via pip and initialize the MCPServerStreamableHttp client with your Vinkius endpoint. Pass this server instance directly into your Agent constructor using the mcpservers list to auto-discover all ten rental tools.

Q: Can I run order pickups asynchronously with this setup?

Yes, use the SDK's async context manager to trigger startorder when a barcode is scanned. This allows your OpenAI agent to process multiple physical returns in parallel.

Run your Booqable rental operations directly inside OpenAI Agents SDK with built-in guardrails and automatic tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Booqable MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Booqable inventory checks with OpenAI Agents SDK

The `check_availability` tool lets your OpenAI agents inspect Booqable stock counts for specific dates before writing any code. By exposing your rental catalog via `list_product_groups`, the SDK maps your real-time inventory levels directly to your agent's reasoning loop. You don't have to write manual API wrappers or validation logic. When an agent needs to know if a camera or bike is free next Tuesday, it queries the MCP Server directly, keeping your booking pipeline accurate.

Secure rental order creation with built-in guardrails

Your OpenAI agents use `create_order` to build new rental bookings based on customer chat history. Because the OpenAI Agents SDK supports strict execution guardrails, you can intercept the order payload before it hits Booqable, preventing accidental double-bookings or pricing errors. This setup lets you hand off complex tasks between specialized agents. One agent handles customer lookups via `get_customer`, while another handles the actual booking, keeping your rental workflows isolated and safe.

Real-time fulfillment tracking through the OpenAI dashboard

The `start_order` and `stop_order` tools let your agents manage the physical pickup and return lifecycle of any rental using this MCP Server. Every single state change is logged and traced directly in your OpenAI dashboard, so you can debug failed handoffs instantly. If a customer returns gear late, the agent checks the order status using `get_order`. It then marks the rental as stopped without requiring you to build a custom backend dashboard.

Setup guide

Set up Booqable 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 Booqable tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip and initialize the `MCPServerStreamableHttp` client with your Vinkius endpoint. Pass this server instance directly into your Agent constructor using the `mcp_servers` list to auto-discover all ten rental tools.

Yes. You can control tool access by defining specific agent boundaries or routing rules in your SDK configuration, ensuring a customer-facing agent can only check stock while an admin agent runs `create_order`.

The SDK relies on the underlying Vinkius MCP Server infrastructure to queue requests. If your rental agent spams `list_orders` or `list_customers`, Vinkius manages the throttling so your OpenAI agent doesn't crash during high-traffic booking windows.

Yes, use the SDK's async context manager to trigger `start_order` when a barcode is scanned. This allows your OpenAI agent to process multiple physical returns in parallel.

Vinkius runs the Booqable connector inside an isolated V8 sandbox. Your customer PII retrieved via `get_customer` and order details from `get_order` are never stored on Vinkius servers, maintaining a strict zero-trust data path directly to OpenAI.

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