About Nutritionix MCP Server
Nutritionix MCP Server gives AI agents access to Nutritionix food search, nutrition data, and exercise calorie estimates for health, fitness, and dietary workflows. It can parse meal descriptions written in natural language.
Key features
- 01Search common and branded foods
- 02Parse meals from natural language
- 03Provide nutrition data
- 04Estimate calories burned by exercise
Use cases
- 01Look up food nutrition information
- 02Turn meal descriptions into nutrition breakdowns
- 03Estimate calories burned by running, cycling, or yoga
MCP support
The MCP server exposes Nutritionix API capabilities as tools for MCP clients, including food search, meal nutrition parsing, and exercise calorie estimates.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README🥦 Nutritionix MCP Server
This is an MCP (Model Context Protocol) server for integrating with the Nutritionix API, enabling AI agents to access food search, nutrition data, and exercise calorie estimates via natural language input.
The goal of this project is to expose Nutritionix's functionality through MCP-compatible tools that can be used seamlessly by large language models and agent frameworks.
🧠 What is MCP?
MCP (Model Context Protocol) is a lightweight protocol designed to let AI agents interact with external tools and APIs in a structured and modular way. Think of it like USB for AI — this server acts as a "driver" for the Nutritionix platform.
With this MCP server, AI models can:
- 🔍 Search for common and branded food items
- 🍽️ Parse natural language meals into nutritional breakdowns
- 🏃 Estimate calories burned from exercises like running, cycling, or yoga
🚀 How to Run
To use this MCP server, you'll need:
✅ Prerequisites
- Python 3.11+
uv– a modern Python package manager- A supported LLM (e.g., Claude)
- A Nutritionix API App ID and App Key – get them at developer.nutritionix.com
Add this to Claude Desktop config
{
"mcpServers": {
"nutritionix-mcp": {
"command": "uvx",
"args": [
"nutritionix-mcp-server",
"--app-id",
"YOUR APP ID",
"--app-key",
"YOUR APP KEY"
]
}
}
}
🤝 Contributions Welcome!
Whether you're into nutrition tech, AI agent development, or API tooling — we’d love your help improving this project. You can contribute by:
- Adding new tools (e.g., barcode search, food logging)
- Improving response formatting
- Writing tests or documentation
- Suggesting new ideas via Issues or Discussions
Feel free to fork, explore, and submit a PR. Let’s make agent-integrated nutrition smarter, together. 🧠🥗
MCP-FORGE – Building tools for the future of intelligent automation.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.