How accurate is the NLP food analysis?

Nutritionix's NLP engine is used by major fitness and health apps globally. It can parse complex meal descriptions including quantities, cooking methods, and brand names with high accuracy, backed by a verified database of 1M+ food items.

Can it recognize branded foods or restaurant items?

Yes, Nutritionix excels at this. If you type '1 Big Mac and a medium fries from McDonald's', it will correctly map these to specific branded items in its database.

Does it track micronutrients?

Yes, in addition to macros (proteins, fats, carbs), it returns data on dietary fiber, sugars, sodium, cholesterol, and potassium for an incredibly comprehensive nutritional profile.

Nutritionix MCP Server for OpenAI Agents SDK 2 tools — connect in under 2 minutes

Name: Nutritionix
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 2 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Nutritionix through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Nutritionix Assistant",
            instructions=(
                "You help users interact with Nutritionix. "
                "You have access to 2 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Nutritionix"
        )
        print(result.final_output)

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 Nutritionix MCP Server

The Nutritionix MCP Server gives your AI agent access to the industry's most advanced natural language food analysis engine.

The OpenAI Agents SDK auto-discovers all 2 tools from Nutritionix through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Nutritionix, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

Core Capabilities

NLP Food Analysis — Type anything like "3 slices of pizza and a diet coke" and get instant, precise nutritional breakdown per item.
Comprehensive Macros — Returns calories, protein, fat, carbs, fiber, sugar, sodium, and cholesterol per serving.
Instant Search — Search the Nutritionix database of common and branded foods including restaurant chains.
Restaurant Coverage — Extensive menu item data from national and regional restaurant chains.

Requires app_id and app_key from Nutritionix. The gold standard for NLP food tracking used by major fitness and health apps.

The Nutritionix MCP Server exposes 2 tools through the Vinkius. Connect it to OpenAI Agents SDK 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 Nutritionix to OpenAI Agents SDK via MCP

Follow these steps to integrate the Nutritionix MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 2 tools from Nutritionix

Why Use OpenAI Agents SDK with the Nutritionix MCP Server

OpenAI Agents SDK provides unique advantages when paired with Nutritionix through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Nutritionix + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Nutritionix MCP Server delivers measurable value.

Automated workflows: build agents that query Nutritionix, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Nutritionix, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Nutritionix tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Nutritionix to resolve tickets, look up records, and update statuses without human intervention

Nutritionix MCP Tools for OpenAI Agents SDK (2)

These 2 tools become available when you connect Nutritionix to OpenAI Agents SDK via MCP:

analyze_food_nutrition

g. "3 slices of pizza and a coke", "1 cup of brown rice", "grilled salmon 200g") and get instant, precise nutritional breakdown including calories, protein, fat, carbs, fiber, sugar, sodium, and cholesterol. The most advanced NLP food parsing engine available. Analyze nutritional content of any food using natural language — powered by Nutritionix NLP

search_nutritionix_foods

Returns both generic foods and brand-specific items with calorie data. Search Nutritionix for common and branded food items

Example Prompts for Nutritionix in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Nutritionix immediately.

"Analyze the nutrition of 2 eggs, 1 toast with butter, and a glass of orange juice."

"Calculate the macros for 1 cup of oatmeal with a sliced banana and a tablespoon of peanut butter."

"How many calories in a Starbucks Grande Caramel Macchiato with almond milk?"

Troubleshooting Nutritionix MCP Server with OpenAI Agents SDK

Common issues when connecting Nutritionix to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Nutritionix + OpenAI Agents SDK FAQ

Common questions about integrating Nutritionix MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.