How to Use the Brilliant Made MCP in OpenAI Agents SDK

Q: How do I configure the Brilliant Made MCP Server with OpenAI Agents SDK?

Install openai-agents via pip, then instantiate MCPServerStreamableHttp using your Vinkius endpoint. Pass this server instance inside the mcpservers list when initializing your agent.

Q: Can OpenAI Agents SDK handle bulk orders on Brilliant Made?

Yes. The agent uses listorders to check existing shipments and then triggers the MCP tool to execute createorder in a loop.

Q: How does caching work with Brilliant Made on OpenAI Agents SDK?

You set cacheToolsList=True in your python code. This prevents the SDK from querying the MCP schema on every turn, making swag lookups much faster.

Q: What happens if a swag item goes out of stock during an execution?

The agent calls getinventorystatus first. If the item is unavailable, the run stops before calling createorder, preventing API errors.

Run secure, self-correcting swag campaigns by exposing Brilliant Made inventory directly to your OpenAI Agents SDK via our managed 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 Brilliant Made MCP to OpenAI Agents SDK

Create your Vinkius account to connect Brilliant Made 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 Brilliant Made with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Swag Orders via OpenAI Agents SDK

Your agent uses `create_order` and `cancel_order` to programmatically handle physical shipments without human intervention. This setup uses OpenAI's built-in guardrails to verify that order quantities and shipping addresses match your corporate guidelines before the API call executes. If a team member requests a package that exceeds their budget, the agent halts the execution. You get full execution tracing inside your OpenAI dashboard, letting you audit every single physical shipment request.

Automatic Inventory and Variant Audits

The agent calls `get_inventory_status` and `get_product_variant` to keep your internal catalogs synchronized with actual warehouse stock. This MCP toolset runs in the background, allowing specialized agents to pass off tasks when stock runs low. When items dip below threshold levels, one agent can trigger a restocking workflow while handing off the customer-facing communication to a support agent. Setting `cacheToolsList=True` ensures these inventory checks happen instantly without extra round trips.

Managed Storefront Gift Cards

Your agent runs `create_gift_card` and `list_gift_cards` to distribute rewards to your developers or customers automatically. It plugs directly into your python deployment via `MCPServerStreamableHttp` to issue real-time store credit. By avoiding manual code for every gift card generation, you let the OpenAI Agents SDK handle the logic safely. You define the budget limits, and the agent executes the distribution.

Setup guide

Set up Brilliant Made 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 Brilliant Made tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip, then instantiate `MCPServerStreamableHttp` using your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when initializing your agent.

Yes. The agent uses `list_orders` to check existing shipments and then triggers the MCP tool to execute `create_order` in a loop.

You set `cacheToolsList=True` in your python code. This prevents the SDK from querying the MCP schema on every turn, making swag lookups much faster.

The agent calls `get_inventory_status` first. If the item is unavailable, the run stops before calling `create_order`, preventing API errors.

All communications go through an ephemeral, zero-trust V8 sandbox. Your corporate shipping addresses, recipient names, and gift card balances are never stored on Vinkius servers.

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