Nutri-Score is a front-of-pack nutrition label that rates food products from A (healthiest) to E (least healthy). It's widely used across Europe and helps consumers make informed dietary choices at a glance.

What is the NOVA classification?

The NOVA classification assigns a score from 1 to 4 depending on how much a food is processed. 1 means unprocessed/minimally processed foods, while 4 indicates ultra-processed food and drink products.

Is the allergen data reliable?

The allergen data is derived from product labels uploaded by contributors. While extensive, you should always double-check physical packaging for severe allergies as formulations can change.

Open Food Facts MCP Server for Pydantic AI 2 tools — connect in under 2 minutes

Name: Open Food Facts
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 2 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Open Food Facts through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Open Food Facts "
            "(2 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Open Food Facts?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Open Food Facts MCP Server

The Open Food Facts MCP Server connects your AI agent to the world's largest open food product database — over 2 million products from 150+ countries.

Pydantic AI validates every Open Food Facts tool response against typed schemas, catching data inconsistencies at build time. Connect 2 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

Core Capabilities

Barcode Scanner — Instantly look up any packaged food product by its EAN/UPC barcode to get complete nutritional information.
Product Search — Find products by name, brand, or category across the entire global database.
Nutri-Score — Official A-to-E nutritional quality grading used across Europe.
NOVA Classification — Food processing level indicator (1=unprocessed to 4=ultra-processed).
Allergen Detection — Comprehensive allergen warnings including gluten, dairy, nuts, soy, and more.

Zero authentication required. Open source, community-driven data. Essential for health apps, dietary assistants, and grocery shopping tools.

The Open Food Facts MCP Server exposes 2 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Open Food Facts to Pydantic AI via MCP

Follow these steps to integrate the Open Food Facts MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 2 tools from Open Food Facts with type-safe schemas

Why Use Pydantic AI with the Open Food Facts MCP Server

Pydantic AI provides unique advantages when paired with Open Food Facts through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Open Food Facts integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Open Food Facts connection logic from agent behavior for testable, maintainable code

Open Food Facts + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Open Food Facts MCP Server delivers measurable value.

Type-safe data pipelines: query Open Food Facts with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Open Food Facts tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Open Food Facts and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Open Food Facts responses and write comprehensive agent tests

Open Food Facts MCP Tools for Pydantic AI (2)

These 2 tools become available when you connect Open Food Facts to Pydantic AI via MCP:

scan_food_barcode

Returns Nutri-Score, NOVA classification, full macronutrient profile, allergens, and ingredient list. Scan a food product barcode to get complete nutritional and allergen information

search_food_products

Returns nutritional information, Nutri-Score grades, NOVA processing levels, and allergen data for each product. Search the Open Food Facts database for packaged food products

Example Prompts for Open Food Facts in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Open Food Facts immediately.

"Scan barcode 3017620422003"

"Search for vegan protein bars with a Nutri-Score of A."

"What is the NOVA group for a standard can of Coca-Cola?"

Troubleshooting Open Food Facts MCP Server with Pydantic AI

Common issues when connecting Open Food Facts to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Open Food Facts + Pydantic AI FAQ

Common questions about integrating Open Food Facts MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Open Food Facts MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.