How to Use the Deliveroo MCP in Pydantic AI

Q: What is the setup process for Deliveroo and Pydantic AI?

Grab the package using pip install pydantic-ai-slimmcp. Instantiate MCPToolset with your Vinkius endpoint URL. Add that object to the toolsets array on your Agent.

Type-safe Deliveroo order management for Pydantic AI. Catch POS injection errors and missing items at runtime.

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 Pydantic AI

Create your Vinkius account to connect Deliveroo to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-check Deliveroo payloads in Pydantic AI

The `get_orders` tool returns active delivery queues directly into your validated data structures. If the API drops a required field, the framework throws a loud validation error instead of silently passing bad data to the kitchen. Accepting these requests requires the `update_order_status` action within 10 minutes. You define exact Pydantic models for the acceptance payload to guarantee your agent never hallucinates an invalid status code.

Report POS injection status

The `create_sync_status` function pushes success or failure notifications back to the platform when tickets hit your local register. Correctness matters here, as dropped syncs through the MCP Server lead to unfulfilled meals. Kitchen display systems rely on `create_prep_stage` to update drivers. Your agent maps internal cooking states to strict literal types before firing the tool.

Fetch single records via MCP Server

The `get_order` tool isolates a single transaction for deep inspection. Model-agnostic agents use this to parse complex dietary restrictions into strict boolean flags. Implementing this requires the unified MCPToolset approach pointing to your Vinkius HTTP endpoint. The framework handles the Streamable HTTP transport while you focus on defining the response schema.

Setup guide

Set up Deliveroo MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "deliveroo-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Deliveroo tools.",
)

result = await agent.run("List recent Deliveroo transactions")
print(result.output)

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 Pydantic AI

Grab the package using pip install pydantic-ai-slim[mcp]. Instantiate MCPToolset with your Vinkius endpoint URL. Add that object to the toolsets array on your Agent.

The framework validates every MCP response against your defined models at runtime. Unexpected schemas trigger immediate exceptions. This stops corrupted tickets from reaching your POS.

Your agent handles the logic. It must pull the queue and fire the acceptance tool within the 10-minute SLA. Type validation ensures the payload format is always correct.

That class is deprecated in current versions. You should always use the unified toolset approach for remote connections.

Vinkius routes your requests through an isolated V8 sandbox that terminates after execution. Dietary restrictions, customer names, and prep stage timestamps are never cached. The zero-trust architecture guarantees data only flows between the API and your local 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