How to Use the Fizzpa MCP in OpenAI Agents SDK

Q: How does Fizzpa integrate with the OpenAI Agents SDK?

You register the server using the MCPServerStreamableHttp class in your Python code. The OpenAI Agents SDK automatically discovers all twelve tools, allowing your agents to manage menus and orders.

Q: How do I handle failed order updates with this setup?

The agent intercepts errors from updateorderinfo and uses its built-in reasoning to retry or alert a human. Every step is logged in your OpenAI tracing dashboard for debugging.

Build self-correcting restaurant dispatch agents that manage orders and menus directly through the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fizzpa MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Fizzpa Order Routing with OpenAI Agents SDK

The `create_new_order` tool lets your OpenAI agents process incoming restaurant orders directly from your digital menu. You pass the customer name and line items to the agent, which handles the transaction. If a customer changes their mind, the agent invokes `cancel_order` or updates the ticket using `update_order_info` without manual intervention. This OpenAI python SDK tracks these Fizzpa ticket updates on your active dashboard. If an agent tries to modify a completed ticket, built-in guardrails block the call before it hits the Fizzpa API. You get complete OpenAI tracing for every Fizzpa ticket change.

Prevent Menu Overselling via MCP Server

This MCP Server exposes the `list_inventory_levels` tool to check physical stock levels before your agent confirms a food order. Your agent queries the warehouse locations with `list_warehouse_locations` to locate the nearest kitchen. If an ingredient runs out, the agent automatically flags the item as unavailable. Handing off tasks between specialized OpenAI agents keeps your restaurant checkout responsive. A front-of-house OpenAI agent takes the ticket, then hands off to a backend agent checking Fizzpa stock. This OpenAI handoff pattern prevents race conditions during high-volume Fizzpa dinner rushes.

Self-Healing Connection Diagnostics

The `check_api_health` tool verifies the connection between your OpenAI agents and the digital menu backend. Your OpenAI agent runs this test during startup to verify Fizzpa credentials. If the Fizzpa endpoint is unreachable, the OpenAI SDK halts execution before customers experience failed checkouts. Running this check with `get_account_profile` confirms that your OpenAI agent holds active Fizzpa permissions. You configure the Fizzpa streamable HTTP parameters once, and the OpenAI agent auto-discovers these tools on boot.

Setup guide

Set up Fizzpa 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 Fizzpa tools at runtime.
3

Create your Agent

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

Run the agent

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

You register the server using the `MCPServerStreamableHttp` class in your Python code. The OpenAI Agents SDK automatically discovers all twelve tools, allowing your agents to manage menus and orders.

Yes, you control this by configuring the agent's tool access parameters during initialization. If you only want to allow stock checks, you expose `list_inventory_levels` while blocking `cancel_order`.

Your primary router agent takes the customer input, then hands off to an inventory agent using `list_inventory_levels`. Once validated, a third agent executes `create_new_order` to finalize the sale.

The agent intercepts errors from `update_order_info` and uses its built-in reasoning to retry or alert a human. Every step is logged in your OpenAI tracing dashboard for debugging.

Your customer names and order histories stay within your local V8 sandbox environment. The MCP Server transmits this sensitive data directly to the endpoint over HTTPS, bypassing third-party storage.

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