How to Use the Deliveroo MCP in AutoGen

Q: How do I add Deliveroo tools to an AutoGen setup?

Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius endpoint. Pass the resulting list directly to your AssistantAgent constructor.

Q: Does AutoGen handle the Deliveroo MCP Server schemas?

Yes, the McpToolAdapter translates standard MCP JSON schemas into AutoGen's native format. You do not need to write custom parsers for the order data.

Deploy debating AutoGen agents to manage Deliveroo order acceptance and POS synchronization.

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 AutoGen

Create your Vinkius account to connect Deliveroo to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Deliveroo order acceptance with AutoGen

`update_order_status` forces your AutoGen agents to reach a consensus before accepting or rejecting a ticket. A kitchen capacity agent monitors current load while a revenue agent pushes to accept everything. These two personas debate the merits of taking on more work during peak hours. Once they agree, the system executes the tool call well before the ten-minute timeout limit.

Broadcast active orders to multiple agents

The `get_orders` and `get_order` endpoints feed live ticket data into your multi-agent conversation. You configure a dedicated monitoring agent to poll this information and broadcast it to the group. Other agents read this broadcast and decide if they need to act. A security persona might flag unusual order volumes, prompting a discussion about potential POS injection failures.

Divide POS sync tasks via Deliveroo MCP Server

`create_prep_stage` and `create_sync_status` allow your conversational framework to report progress back to the platform. This Deliveroo MCP Server integrates perfectly with AutoGen's `McpToolAdapter` for automatic schema conversion. One agent claims responsibility for tracking the physical cooking process. It triggers the prep stage tool independently while the rest of the swarm handles POS synchronization.

Setup guide

Set up Deliveroo MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Deliveroo tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Deliveroo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Deliveroo data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Deliveroo_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Deliveroo data")
    print(result.messages[-1].content)

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 AutoGen

Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius endpoint. Pass the resulting list directly to your `AssistantAgent` constructor.

Yes, you can assign different system prompts to multiple agents, forcing them to negotiate before calling `update_order_status`. They evaluate kitchen load before making a decision.

Yes, the `McpToolAdapter` translates standard MCP JSON schemas into AutoGen's native format. You do not need to write custom parsers for the order data.

Yes, your framework can distribute tasks among specialized agents. One persona can monitor `create_prep_stage` while another handles POS synchronization.

The MCP Server handles raw order payloads and POS sync statuses. Vinkius manages all authentication at the infrastructure level, isolating your agent's requests in a secure, ephemeral environment.

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