Food Tracker MCP Server

Food Tracker MCP Server

Enables tracking food intake and nutrition using the USDA FoodData Central database. Supports logging meals, setting daily nutrition goals, viewing food diaries, and analyzing nutrition trends over time with local SQLite storage.

Category
Visit Server

README

Food Tracker MCP Server

A Model Context Protocol (MCP) server for tracking food intake and nutrition using the USDA FoodData Central database.

Features

  • Search Foods: Query the USDA FoodData Central database for nutritional information
  • Log Meals: Record food intake with calories, macros, and serving sizes
  • Track Progress: View daily logs with totals compared to your goals
  • Set Goals: Define daily targets for calories, protein, carbs, and fat
  • Get Summaries: View nutrition averages over days, weeks, or months

Installation

Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "food-tracker": {
      "command": "npx",
      "args": ["-y", "@neonwatty/food-tracker-mcp"],
      "env": {
        "USDA_API_KEY": "your_api_key_here"
      }
    }
  }
}

Claude Code

claude mcp add food-tracker -e USDA_API_KEY=your_api_key -- npx -y @neonwatty/food-tracker-mcp

Or add to ~/.claude.json:

{
  "mcpServers": {
    "food-tracker": {
      "command": "npx",
      "args": ["-y", "@neonwatty/food-tracker-mcp"],
      "env": {
        "USDA_API_KEY": "your_api_key_here"
      }
    }
  }
}

Requirements

USDA API Key

Get your free API key at: https://fdc.nal.usda.gov/api-key-signup/

Available Tools

search_food

Search the USDA FoodData Central database for foods.

"Search for chicken breast"

Returns nutrition information per 100g serving including calories, protein, carbs, and fat.

log_food

Log a food entry to your daily food diary.

"Log 200g of grilled salmon for lunch with 400 calories, 40g protein, 0g carbs, 22g fat"

Parameters:

  • food_name (required): Name of the food
  • serving_size (required): Amount of the serving
  • serving_unit (required): Unit (g, oz, cup, piece, etc.)
  • calories (required): Calories for this serving
  • protein_g: Protein in grams
  • carbs_g: Carbohydrates in grams
  • fat_g: Fat in grams
  • fiber_g: Fiber in grams
  • meal: breakfast, lunch, dinner, or snack
  • date: Date in YYYY-MM-DD format (defaults to today)

get_daily_log

Get all food entries for a specific day with totals and goal comparison.

"What have I eaten today?"
"Show me my food log for 2025-01-15"

set_goals

Set your daily nutrition goals.

"Set my daily goal to 2000 calories with 150g protein, 200g carbs, and 65g fat"

get_summary

Get nutrition summary and averages for a date range.

"Show me my nutrition summary for this week"
"Get my monthly nutrition averages"

delete_entry

Delete a food log entry by its ID.

"Delete entry 5"

Data Storage

Food logs are stored locally in a SQLite database at ~/.food-tracker/food.db. Your data never leaves your machine.

Example Conversation

You: Search for oatmeal Claude: Found 10 foods matching "oatmeal"...

You: Log 1 cup of oatmeal for breakfast Claude: Logged: Oatmeal (1 cup) - 150 cal | P: 5g | C: 27g | F: 3g

You: What have I eaten today? Claude: Food Log for 2025-01-15...

License

MIT License - see LICENSE for details.

Contributing

Contributions are welcome! Please open an issue or submit a pull request on GitHub.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured