How to Use the iFood MCP in Pydantic AI

Q: How does Pydantic AI validate iFood menu items?

It uses Pydantic models to inspect the output of getcatalog. If the returned data doesn't match your schema, the agent throws a validation error immediately.

Q: Is the iFood MCP Server compatible with Pydantic AI?

It is fully compatible. You can connect it via the MCPToolset class and define your agent to interact with any of the 11 available iFood tools.

Use Pydantic AI for type-safe iFood management. Validate every order and catalog action with strict runtime schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect iFood MCP to Pydantic AI

Create your Vinkius account to connect iFood 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 iFood with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Catalog Updates

Ensure your menu data is always valid before pushing updates. Pydantic AI validates every response from `get_catalog` against your predefined models. When you use `update_catalog_item`, the agent verifies that the price and availability fields meet your strict requirements. This prevents silent corruption of your menu data.

Structured Order Processing

Handle incoming orders with total confidence. The agent uses `get_orders` to fetch data, and your models validate the order number, customer details, and item totals instantly. If the data structure shifts unexpectedly, the agent fails immediately. This forces you to handle errors explicitly, keeping your fulfillment pipeline stable.

Verified Logistics Dispatch

Manage driver assignments with rigorous schema enforcement. The `assign_driver` tool requires specific IDs, and your agent ensures these inputs are valid before sending them to iFood. Use `get_logistics` to confirm status updates. By strictly typing these interactions, you ensure your fulfillment logic remains predictable and reliable.

Setup guide

Set up iFood 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": {
        "ifood-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent iFood 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 iFood. 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 iFood 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 iFood MCP in Pydantic AI

It uses Pydantic models to inspect the output of `get_catalog`. If the returned data doesn't match your schema, the agent throws a validation error immediately.

Yes, you can define models for your order status updates. Calling `update_order_status` through your agent ensures the status string conforms to valid fulfillment states.

It is fully compatible. You can connect it via the `MCPToolset` class and define your agent to interact with any of the 11 available iFood tools.

Access is restricted to your authenticated session. The server only touches the specific order and catalog records you explicitly request through the toolset.

It does. Because every tool call is validated against a schema, your agent cannot pass malformed IDs or incorrect data types to the iFood backend.

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