Local MCP server for searching 300,000+ foods, nutrition facts, and barcodes from the OpenNutrition database.
Claude Desktop config.json'a ekle
{
"mcpServers": {
"deadletterq-mcp-opennutrition": {
"command": "node",
"args": [
"~/.mcp/mcp-opennutrition/index.js"
]
}
}
} Kaynak kodu al ve yerel olarak çalıştır
git clone https://github.com/deadletterq/mcp-opennutrition.git ~/.mcp/mcp-opennutrition
cd ~/.mcp/mcp-opennutrition A Model Context Protocol (MCP) server providing access to the comprehensive OpenNutrition food database with 300,000+ food items, nutritional data, and barcode lookups.
OpenNutrition addresses the longstanding issues with fragmented and unreliable nutritional data by combining authoritative public sources (USDA, CNF, FRIDA, AUSNUT). Unlike other databases that suffer from inconsistent user-generated content or restrictive commercial licensing, OpenNutrition provides transparent, comprehensive, and accurate nutritional data that’s freely accessible to developers and researchers.
The easiest way to run the server is via Docker. No build steps required.
Run the container:
docker run --rm -p 9113:3000 deadletterq/mcp-opennutrition
Then add to your MCP configuration:
"mcp-opennutrition": {
"type": "streamable-http",
"url": "http://localhost:9113"
}
Install dependencies:
npm install
Build the project:
npm run build
Add to your MCP configuration (set the same version of node that you used to build the project):
"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"
]
}
This server uses the OpenNutrition dataset.
The dataset provides comprehensive nutritional profiles including macronutrients, vitamins, and minerals.
Once configured, the MCP server runs fully locally on your machine and automatically provides food and nutrition query capabilities to Claude/Cline. All data processing and queries happen locally with no external API calls, ensuring privacy and fast response times.
Here is an example of how Claude uses the tool for a brownie recipe:

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Search ArXiv research papers
Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Web search using free multi-engine search (NO API KEYS REQUIRED) — Supports Bing, Baidu, DuckDuckGo, Brave, Exa, and CSDN.
Web search using DuckDuckGo
Web search capabilities using Brave's Search API