DataBody for Claude Desktop
Use the Model Context Protocol (MCP) to access DataBody directly from Claude Desktop. Log meals, check your macros, and manage your nutrition without leaving your AI assistant.
What is the Model Context Protocol?
The Model Context Protocol (MCP) is an open standard that lets AI assistants like Claude connect to external tools and data sources. Instead of copying and pasting between apps, you can interact with DataBody directly through natural conversation.
Natural Language
Just tell Claude what you ate and it logs it for you
Real Actions
Claude executes tools to update your actual DataBody account
Secure Auth
OAuth 2.0 with PKCE keeps your data safe
Installation
Prerequisites
Make sure you have:
- check_circle Claude Desktop installed
-
check_circle
Node.js 20+ (
node --version) - check_circle A DataBody account
Install the MCP Server
Choose one of these installation methods:
Option A: Download MCPB Bundle
The easiest option. Download a single file that contains everything pre-bundled. No npm or Node.js installation required on your system.
download Download databody-mcp.mcpbAfter downloading, double-click the file or drag it onto Claude Desktop to install.
Option B: Install via npm
If you have Node.js installed, you can install the MCP server globally via npm. This makes updates easier with npm update -g.
npm install -g @databody/mcp
Option C: Build from Source
For developers who want to customize or contribute to the MCP server.
# Clone the repository
git clone https://github.com/databody-ai/databody-mcp.git
cd databody-mcp
# Install dependencies and build
npm install
npm run build
Configure Claude Desktop
If you downloaded the MCPB bundle:
No manual configuration needed! Simply double-click the .mcpb file or drag it onto Claude Desktop. The server will be installed and configured automatically.
If you installed via npm or built from source, add the following to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
For npm install:
{
"mcpServers": {
"databody": {
"command": "npx",
"args": ["-y", "@databody/mcp"],
"env": {
"DATABODY_API_URL": "https://databody.ai"
}
}
}
}
For source install:
{
"mcpServers": {
"databody": {
"command": "node",
"args": ["/path/to/databody-mcp/dist/index.js"],
"env": {
"DATABODY_API_URL": "https://databody.ai"
}
}
}
}
Replace /path/to/databody-mcp with the actual path where you cloned the repository.
Authenticate
Restart Claude Desktop and ask it to authenticate with DataBody:
"Connect to DataBody" or "Authenticate with DataBody using browser"
A browser window will open for secure OAuth login. Once authenticated, your token is stored locally in ~/.databody_token.json.
Example Usage
Log a Meal
"I had 2 scrambled eggs, avocado toast, and a coffee for breakfast"
Claude will parse this, estimate macros, and log it to your account.
Check Progress
"How am I doing on my macros today?"
Get a summary of today's intake vs your targets.
Get Suggestions
"What high-protein dinner can I make with 600 calories left?"
AI-powered meal suggestions based on your remaining macros.
Household Planning
"Plan dinner for my family tonight"
Get household members' goals and suggest meals that work for everyone.
Set Preferences
"Remember that I'm lactose intolerant"
Save notes that persist and inform future suggestions.
Analyze Photos
"What's in this meal?" [attach photo]
AI vision identifies foods and estimates macros from images.
Grocery Shopping
"Create a grocery list for Trader Joe's with a $75 budget"
Create lists, add items, track spending, and get smart suggestions.
Check Off Items
"I just picked these up" [attach photo of groceries]
Send a photo and AI identifies and checks off items from your list.
Available Tools
The DataBody MCP server exposes 50+ tools organized by category. Claude automatically selects the right tools based on your requests.
Authentication
- authenticate (browser/password)
- logout
- auth_status
User Profile
- get_user_profile
- update_user_profile
- change_password
- change_email
Health & Summary
- get_health_summary
- get_health_history
Nutrition
- get_today_nutrition
- get_nutrition_history
- log_food
- update_nutrition_log
- delete_nutrition_log
- add_nutrition_item
- delete_nutrition_item
Food Search
- search_food
- get_food_details
- barcode_lookup
- get_favorites / add_favorite
- get_recents
AI Features
- ai_chat
- get_meal_suggestions
- analyze_photo
- parse_food_description
- expand_meal_ingredients
- get_daily_greeting
- get_token_usage
Chat Threads
- list_chat_threads
- get_chat_thread
- create_chat_thread
- delete_chat_thread
- generate_thread_title
- get_chat_history
Goals
- get_current_goal
- list_goals
- create_goal
- update_goal
- delete_goal
- calculate_goal
Workouts
- get_recent_workouts
- list_workouts
- create_workout
- update_workout
- delete_workout
Notes & Memory
- get_notes
- create_note
- update_note
- delete_note
Households
- get_households
- get_household_summary
- create/update/delete_household
- list_household_members
- suggest_meal_to_member
Household Invites
- list_household_invites
- list_pending_invites
- create_household_invite
- accept_invite / decline_invite
- accept_invite_by_token
Grocery Lists
- create_grocery_list
- get_grocery_lists
- get_grocery_list
- update/delete_grocery_list
- add_grocery_items
- check/uncheck_grocery_items
- set_item_prices
- get_fridge_inventory
- suggest_grocery_items