OpenNutrition
The OpenNutrition MCP server connects your AI assistant with a massive database of 300,000+ food items and their complete nutritional profiles.
It combines authoritative sources like USDA, CNF, FRIDA, and AUSNUT into one database. You get consistent, accurate nutritional data without the headaches of user-generated content errors or expensive commercial API limitations.
Features
- 🔍 Name-based Search: Find foods by name, brand, or partial text matches
- 📱 Barcode Lookup: Query foods using EAN-13 barcodes for instant identification
- 🗂️ Browsing Interface: Paginated access to the complete food database
- 📊 Detailed Nutrition Data: Complete macronutrient, vitamin, and mineral profiles
- 💻 Local Processing: All queries run locally with no external API dependencies
- 🔒 Privacy-First: No data leaves your machine during food lookups
Use Cases
- Nutrition App Development: Build calorie-tracking or meal-planning apps with reliable food data instead of maintaining your incomplete database
- Research Applications: Access standardized nutritional data for academic studies without worrying about data consistency across different food sources
- Recipe Analysis: Calculate precise nutritional breakdowns for recipes by looking up individual ingredients and their quantities
- Health Platform Integration: Add comprehensive food lookup capabilities to wellness platforms without complex database management
How to Use It
1. Clone or download the MCP OpenNutrition server from GitHub.
2. Install the required dependencies:
npm install3. Build the project:
npm run build4. Add this configuration to your Claude/Cline MCP settings file (use the same Node.js version you built with):
"mcp-opennutrition": {
"command": "/Users/YOUR.USERNAME/.nvm/versions/node/v20.19.0/bin/node",
"args": [
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/mcp-opennutrition/build/index.js"
]
}5. Available Tools:
- search_foods: Search by food name, brand, or partial matches
- browse_foods: Get paginated lists with optional offset parameters
- get_food_by_id: Retrieve complete nutritional data using specific food IDs
- barcode_lookup: Find foods using EAN-13 barcode numbers
6. After configuration, your AI assistant can automatically search for foods, analyze recipes, and provide detailed nutritional breakdowns. The server processes all queries locally, so responses are fast and your data stays private.
FAQs
Q: Does this require an internet connection for food lookups?
A: No. The entire OpenNutrition database runs locally on your machine. Once installed, all food searches and nutritional data queries work offline.
Q: How current is the nutritional data?
A: The server uses the OpenNutrition dataset, which combines data from major authoritative sources including USDA’s food database. This data represents the most comprehensive publicly available nutritional information.
Q: Can I search for branded food products?
A: Yes. The database includes both generic foods and many branded products. You can search by brand name or use barcode lookup for packaged items with EAN-13 codes.
Q: What nutritional information is available for each food?
A: Each food entry includes complete macronutrient data (calories, protein, carbs, fats), vitamins, minerals, and other nutritional components when available from the source databases.
Q: How do I handle foods not found in the database?
A: The database contains 300,000+ items, but some specialty or very new products might not be included. You can use the closest match from search results or fall back to manual nutritional data entry.
Latest MCP Servers
Obsidian Web
Claude Peers
Memo
Featured MCP Servers
Claude Peers
Excalidraw
Claude Context Mode
FAQs
Q: What exactly is the Model Context Protocol (MCP)?
A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.
Q: How is MCP different from OpenAI's function calling or plugins?
A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.
Q: Can I use MCP with frameworks like LangChain?
A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.
Q: Why was MCP created? What problem does it solve?
A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.
Q: Is MCP secure? What are the main risks?
A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.
Q: Who is behind MCP?
A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.
