How to Use the Deliveroo MCP in OpenAI Agents SDK

Q: Does the Deliveroo integration support POS injection tracking with OpenAI Agents SDK?

Your agent handles that explicitly. It executes createsyncstatus to tell the platform whether the local register accepted the ticket. The framework's tracing logs every success or failure.

Wire Deliveroo order management directly into your OpenAI Agents SDK production system using this 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 Deliveroo MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Deliveroo lifecycles via OpenAI Agents SDK

The `get_orders` tool pulls active delivery requests straight into your agent's context window. Your system reads the incoming queue and extracts required items without human intervention. Agents then trigger `update_order_status` to accept or reject tickets within the strict 10-minute SLA window. Guardrails in the framework force your agent to validate inventory before committing to a fulfillment timeline.

Sync kitchen progress and POS data

The `create_prep_stage` endpoint lets your agent update the exact cooking phase for waiting drivers. Handoffs between a specialized POS-sync agent and a kitchen-display agent keep the physical workflow moving. When tickets hit your local register, the agent fires `create_sync_status` to confirm successful injection. Tracing via the OpenAI dashboard logs exactly when the local system acknowledged the payload.

Inspect specific delivery tickets

The `get_order` tool retrieves granular details for a single transaction. You pass the specific ID, and the MCP Server returns exactly what the customer requested along with delivery notes. Setting cacheToolsList=True during initialization drops the overhead of discovering this capability on every run. Production environments rely on this fast retrieval to answer customer support queries instantly.

Setup guide

Set up Deliveroo 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 Deliveroo tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package via pip install openai-agents. Initialize MCPServerStreamableHttp with your Vinkius endpoint token. Pass that object into the mcp_servers array when building your agent.

Yes, as long as you configure the agent to poll the queue. It reads new entries and calls update_order_status to accept them. You must do this within 10 minutes of the request.

Your agent handles that explicitly. It executes create_sync_status to tell the platform whether the local register accepted the ticket. The framework's tracing logs every success or failure.

The platform automatically drops the ticket. Your system must trigger the acceptance tool fast enough to avoid missed revenue.

The Vinkius V8 Isolate Sandbox destroys all memory after your agent finishes executing a tool. Order items, customer delivery notes, and POS injection IDs never touch persistent storage. The ephemeral container exists only long enough to process the specific HTTP request.

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