How to Use the Deliveroo MCP in CrewAI

Q: Can I limit which Deliveroo tools each of my CrewAI agents can use?

Yes. When setting up your agents, you can use toolfilter to specify which tools from the MCP Server each agent can access. This is great for security and for enforcing role-based responsibilities in your crew.

Deploy a team of AI agents to run your Deliveroo operations. CrewAI can monitor, accept, and process orders for you, 24/7.

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 CrewAI

Create your Vinkius account to connect Deliveroo to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Roles for Order Management

CrewAI lets you build a team of agents to handle your Deliveroo workflow. An 'Order Taker' agent can be tasked with constantly polling `get_orders`. When it finds a new one, it passes the details to a 'Kitchen Manager' agent. The 'Kitchen Manager' agent's job is to call `update_order_status` to accept the order. It then uses `create_prep_stage` to update Deliveroo as the kitchen staff works. Each agent has one job, and they do it well.

Build an Autonomous Operations Crew

Go beyond simple task execution. Add a 'POS Sync' agent to your crew whose only responsibility is calling `create_sync_status` to ensure every accepted order makes it into your sales system. This separation of duties makes your system more robust. CrewAI's shared memory means all agents are working with the same information. When the 'Order Taker' gets an order with `get_order`, the 'Kitchen Manager' already has the context it needs to act. This MCP Server provides the tools for them to use.

A Complete Toolset for your CrewAI Agents

This MCP Server equips your agents with all the necessary Deliveroo functions. You can configure your CrewAI setup to give different tools to different agents. Your 'Auditor' agent might only have access to `get_orders`, while the 'Operator' agent gets `update_order_status`. It's a straightforward integration. Just pass your Vinkius MCP URL when defining your agent, and it automatically discovers and registers the five available tools. Your crew is ready to start managing orders in minutes.

Setup guide

Set up Deliveroo MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Deliveroo tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Deliveroo Analyst",
    goal="Access and analyze Deliveroo data via MCP.",
    backstory="Expert analyst with direct Deliveroo access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Deliveroo transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Deliveroo Analyst",
        goal="Access and analyze Deliveroo data via MCP.",
        backstory="Expert analyst with direct Deliveroo access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Deliveroo transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Define an agent for each role: one to watch for new orders using `get_orders`, another to accept them with `update_order_status`, and a third to handle `create_prep_stage` updates. Then define a sequential task list for the crew to execute.

Absolutely, that's the point of CrewAI. One agent can find the order, pass it to a second agent for confirmation, which then hands it off to a third for POS syncing. They use the tools from this MCP Server to interact with Deliveroo at each step.

Yes. When setting up your agents, you can use `tool_filter` to specify which tools from the MCP Server each agent can access. This is great for security and for enforcing role-based responsibilities in your crew.

An autonomous CrewAI agent can check for new orders every minute. Once it finds one, it can immediately execute the task to call `update_order_status`, ensuring you never miss the confirmation window.

Yes. Your CrewAI agents access Deliveroo order details through an encrypted, point-to-point MCP connection. The server infrastructure is sandboxed and ephemeral, meaning your data is processed in memory and never written to disk.

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