How to Use the Uber Eats MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle status updates for Uber Eats?

The agent uses getorders first, pulling a list of all orders and their current statuses. From there, it executes specific actions like calling markorderprepstarted or markorderready to update the customer immediately.

Q: Can I use the OpenAI Agents SDK to check for past Uber Eats complaints?

Yes. You can call getorderissues on a specific order ID. This gives you issue descriptions, timestamps of when problems occurred, and whether any refunds were issued.

Q: What if I need to check multiple restaurant locations with Uber Eats using the OpenAI Agents SDK?

Start by running getstores to pull all your external store IDs. Then, you pass those IDs into other tools like getmenus, making sure every operation is scoped to the right location.

Q: How does the OpenAPI Agents SDK assist with Uber Eats menu changes?

It helps you toggle item availability using updatemenuitemavailability. You just need the store ID and the item ID to mark things as in-stock or out-of-stock.

Manage every step of your Uber Eats operation. Production-grade control via 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 Uber Eats MCP to OpenAI Agents SDK

Create your Vinkius account to connect Uber Eats 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 Uber Eats with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process and track orders with MCP Server

Your AI client uses `get_orders` to list all orders, filtering by status like PENDING or READY. It pulls order IDs, customer info, items ordered, and timestamps across your entire restaurant network. Need to manage the flow? You can use `accept_order` when an order comes in, or call `reject_order` if ingredients run low. The agent handles these critical status changes while keeping a clean audit trail.

Control menus and availability via MCP Server

Want to update what customers can buy? First, the agent runs `get_stores` to grab your external IDs. Then, it uses `get_menus` to review the item catalog. If you run out of basil, for example, you trigger `update_menu_item_availability` to toggle that item's status to unavailable. This prevents orders for items that aren't ready. It keeps your listings accurate and stops agents from trying to fulfill impossible orders.

Confirm order lifecycle with Uber Eats SDK

The `complete_order` tool finalizes the transaction, closing out the entire delivery cycle and triggering payment processing. This step is crucial for accurate revenue tracking. If you confirm delivery happened successfully, the agent calls this function. It’s the definitive signal that all parts—from acceptance to final payment—are done.

Setup guide

Set up Uber Eats 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 Uber Eats tools at runtime.
3

Create your Agent

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

Run the agent

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

The agent uses `get_orders` first, pulling a list of all orders and their current statuses. From there, it executes specific actions like calling `mark_order_prep_started` or `mark_order_ready` to update the customer immediately.

Yes. You can call `get_order_issues` on a specific order ID. This gives you issue descriptions, timestamps of when problems occurred, and whether any refunds were issued.

Start by running `get_stores` to pull all your external store IDs. Then, you pass those IDs into other tools like `get_menus`, making sure every operation is scoped to the right location.

The server tracks order contents and special instructions. This includes specific items ordered, customer names, and the total monetary value of the transaction.

It helps you toggle item availability using `update_menu_item_availability`. You just need the store ID and the item ID to mark things as in-stock or out-of-stock.

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