Does this work for Uber Eats customers or only merchants?

This MCP server is designed exclusively for Uber Eats merchants (restaurant owners). It uses the Uber Eats Marketplace API to manage orders, menus, deliveries, and store operations. Consumer-side features (browsing restaurants, placing orders) require the Uber consumer app. If you're a restaurant owner using Uber Eats for delivery, this is for you.

Can I automatically accept all incoming orders?

Yes! AI agents can monitor pending orders and auto-accept them based on your criteria. You can set up automation rules to accept orders instantly during business hours, reject when kitchen is at capacity, or flag special instructions for manual review. This significantly reduces response times and improves restaurant ratings on the platform.

Does this support multiple restaurant locations?

Absolutely. The API returns all stores associated with your merchant account. Each tool requires a store_id parameter, so you can manage operations independently across all your restaurant locations. AI agents can list all your stores first to get their IDs, then manage menus, orders, and settings for each location separately.

Uber Eats MCP Server for OpenAI Agents SDK 14 tools — connect in under 2 minutes

Name: Uber Eats
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 14 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Uber Eats through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Uber Eats Assistant",
            instructions=(
                "You help users interact with Uber Eats. "
                "You have access to 14 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Uber Eats"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Uber Eats MCP Server

What you can do

Connect AI agents to the Uber Eats Marketplace API for complete restaurant and delivery management:

The OpenAI Agents SDK auto-discovers all 14 tools from Uber Eats through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Uber Eats, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

Monitor incoming orders in real-time with status tracking (PENDING → ACCEPTED → PREPARING → READY → DELIVERED)
Accept or reject orders instantly based on kitchen capacity
Manage restaurant menus — update prices, availability, descriptions, dietary tags
Review order details including customer info, items, special instructions, and totals
Track delivery status with real-time courier GPS location and ETA
Handle order issues including customer complaints and refund requests
View store information and configuration across all registered locations
Mark orders ready for courier pickup when food is prepared

The Uber Eats MCP Server exposes 14 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Uber Eats to OpenAI Agents SDK via MCP

Follow these steps to integrate the Uber Eats MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 14 tools from Uber Eats

Why Use OpenAI Agents SDK with the Uber Eats MCP Server

OpenAI Agents SDK provides unique advantages when paired with Uber Eats through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Uber Eats + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Uber Eats MCP Server delivers measurable value.

Automated workflows: build agents that query Uber Eats, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Uber Eats, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Uber Eats tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Uber Eats to resolve tickets, look up records, and update statuses without human intervention

Uber Eats MCP Tools for OpenAI Agents SDK (14)

These 14 tools become available when you connect Uber Eats to OpenAI Agents SDK via MCP:

accept_order

This notifies the customer that the restaurant is preparing their food and triggers courier assignment by Uber Eats. Required before marking order as ready for pickup. Use this to acknowledge incoming orders and begin food preparation. Should be done promptly to maintain good restaurant ratings. Accept a pending Uber Eats order to confirm preparation

cancel_order

This is different from rejection - cancellation happens after acceptance and may result in customer dissatisfaction and potential platform penalties. Requires a cancellation reason. Use only when absolutely necessary (kitchen emergency, safety issue, or unavoidable circumstance). Cancel an already accepted Uber Eats order

complete_order

This should be called after confirmation that the delivery was successful. Closes the order lifecycle and triggers final payment processing. Use this to confirm order completion. Mark an order as fully completed (delivered and finalized)

get_delivery_status

Use this to track delivery progress, answer customer inquiries about their order, or coordinate with couriers. Get real-time delivery tracking status for an Uber Eats order

get_menus

Use this to review menu structure, check which items are available/out of stock, or get menu item IDs needed for availability updates. Get complete menu catalog for a specific Uber Eats restaurant

get_order

Use this to review order contents before accepting, verify special instructions, or prepare items correctly. Get complete details of a specific Uber Eats delivery order

get_order_issues

Returns issue descriptions, timestamps, resolution status, and any refunds issued. Use this to review and address order problems, improve quality, and handle disputes proactively. Get reported issues and complaints for a specific Uber Eats order

get_orders

Can filter by status: PENDING (awaiting restaurant acceptance), ACCEPTED (restaurant confirmed), PREPARING (food being prepared), READY (ready for courier pickup), DELIVERED (completed), CANCELLED, or REJECTED. Returns order IDs, customer info, items ordered, totals, special instructions, and timestamps. Use this to monitor order flow, track pending orders requiring action, or review completed deliveries. List all orders for your Uber Eats restaurants with optional status filter

get_store

Use this to review store configuration, verify delivery settings, or check operational status. Get detailed information about a specific Uber Eats restaurant/store

get_stores

Returns external store IDs, names, addresses, operating status, and business details. Use this tool first to get your store IDs, which are required for all other menu and order management operations. List all restaurants/stores associated with your Uber Eats merchant account

mark_order_prep_started

Updates order status to PREPARING and notifies the customer. Use this to keep customers informed about their order progress and provide accurate delivery time estimates. Mark that food preparation has started for an accepted order

mark_order_ready

This triggers courier dispatch notification. Use this when food is complete and waiting for courier arrival. Couriers will be routed to your location for pickup. Mark order as ready for courier pickup (food is packaged and waiting)

reject_order

The customer is notified and refunded automatically. Provide a reason code: "item_unavailable" (key ingredients out of stock), "too_busy" (kitchen at capacity), "kitchen_closed" (outside operating hours), or "other". Use this when unable to fulfill an order. Excessive rejections may affect restaurant visibility on the platform. Reject a pending Uber Eats order when unable to fulfill it

update_menu_item_availability

Set available=true to mark item as in-stock and orderable, or available=false to mark as out-of-stock. Common use: quickly mark items as unavailable when ingredients run out, then re-enable when restocked. Requires external store ID and menu item ID from get_menus result. Toggle availability status of a menu item (mark as in-stock or out-of-stock)

Example Prompts for Uber Eats in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Uber Eats immediately.

"Show me all pending orders and accept them automatically"

"Update the price of 'Margherita Pizza' to R$45.90 and mark it as unavailable"

"Track the delivery status of order #12345 and tell me where the courier is"

Troubleshooting Uber Eats MCP Server with OpenAI Agents SDK

Common issues when connecting Uber Eats to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Uber Eats + OpenAI Agents SDK FAQ

Common questions about integrating Uber Eats MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.