OpenNutrition
Provides access to a comprehensive food database with 300,000+ items, enabling nutritional data lookups, food searches, and barcode scanning with all processing happening locally for privacy and speed.
What is OpenNutrition?
OpenNutrition is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides access to a comprehensive food database with 300,000+ items, enabling nutritional data lookups, food searches, and barcode scanning with all processing happening locally for privacy and speed...
Provides access to a comprehensive food database with 300,000+ items, enabling nutritional data lookups, food searches, and barcode scanning with all processing happening locally for privacy and speed.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Provides access to a comprehensive food database with 300,00
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-opennutritionConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use OpenNutrition
MCP OpenNutrition gives AI assistants access to a local database of 300,000+ food items sourced from authoritative datasets including USDA, CNF, FRIDA, and AUSNUT, covering macronutrients, vitamins, and minerals. All processing happens on-device with no external API calls, making it both fast and private. It exposes tools to search foods by name or brand, browse the full catalogue with pagination, retrieve detailed nutrition by ID, and look up products by EAN-13 barcode — making it ideal for nutrition tracking, recipe analysis, and dietary planning applications.
Prerequisites
- Docker installed (recommended deployment method) or Node.js 18+ for source builds
- An MCP-compatible client such as Claude Desktop or Claude Code
- No external API keys required — the food database is bundled locally
Pull and run the Docker image
The fastest way to start is pulling the pre-built Docker image. It starts an HTTP server on port 3000 that the MCP client connects to.
docker run --rm -p 9113:3000 deadletterq/mcp-opennutritionAlternative: build from source
If you prefer a local Node.js setup, clone the repository, install dependencies, and build the TypeScript project.
git clone https://github.com/deadletterq/mcp-opennutrition
cd mcp-opennutrition
npm install
npm run buildConfigure your MCP client for Docker
Add the server to your MCP client config. When using Docker the transport is streamable-http pointing to localhost:9113.
Configure your MCP client for source builds
For a local Node.js build, use the stdio transport pointing directly at the built index.js file.
Test a food search
Ask your AI assistant to search for a food item. The server will query the local database and return nutritional details without any network calls.
OpenNutrition Examples
Client configuration (Docker)
Use this configuration when running the server via Docker on port 9113. Add to your claude_desktop_config.json.
{
"mcpServers": {
"mcp-opennutrition": {
"type": "streamable-http",
"url": "http://localhost:9113"
}
}
}Client configuration (source build)
Use this configuration when running from a local Node.js build. Replace the paths with your actual locations.
{
"mcpServers": {
"mcp-opennutrition": {
"command": "/usr/local/bin/node",
"args": ["/path/to/mcp-opennutrition/build/index.js"]
}
}
}Prompts to try
Example prompts that use the food search, barcode lookup, and nutrition detail tools.
- "What are the nutritional facts for a medium banana?"
- "Search for foods containing 'oat' and show macronutrients"
- "Look up the barcode 5000112546415 and tell me what it is and its calorie count"
- "Compare the protein content of chicken breast vs tofu per 100g"
- "How many calories are in 200g of cooked brown rice?"Troubleshooting OpenNutrition
Docker container starts but MCP client cannot connect
Confirm the container is listening on the mapped port with 'docker ps'. The config url must be http://localhost:9113 — not port 3000, which is the internal container port.
Food search returns no results
The database uses English food names from USDA and other English-language sources. Try shorter or more generic search terms (e.g. 'apple' instead of 'fresh Fuji apple').
Barcode lookup returns nothing
The server supports EAN-13 barcodes indexed in the bundled database. Not all regional products are included — fall back to a name search if the barcode is not found.
Frequently Asked Questions about OpenNutrition
What is OpenNutrition?
OpenNutrition is a Model Context Protocol (MCP) server that provides access to a comprehensive food database with 300,000+ items, enabling nutritional data lookups, food searches, and barcode scanning with all processing happening locally for privacy and speed. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install OpenNutrition?
Follow the installation instructions on the OpenNutrition GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with OpenNutrition?
OpenNutrition works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is OpenNutrition free to use?
Yes, OpenNutrition is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
OpenNutrition Alternatives — Similar Data Science & ML Servers
Looking for alternatives to OpenNutrition? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up OpenNutrition in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use OpenNutrition?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.