Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/dshanklin-bv/mcp-pizza.git
cd mcp-pizza
uv pip install -e .Register it in Claude Code
claude mcp add mcp-pizza -- uv --directory /path/to/mcp-pizza run mcpizzaReplace any placeholder paths in the command with the real path on your machine.
Make your agent remember this setup
mcp-pizza's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Real Domino's API integration for pricing and validation
- Advanced pizza customization with topping and coupon support
- Comprehensive interaction logging for MCP debugging
- AI-powered deal discovery and ordering guidance
- Full implementation of the Model Context Protocol
Tools 12
find_storesFind nearby Domino's by address or zipget_store_infoDetailed store information and hoursget_menuComplete menu with categoriessearch_menuSearch for specific itemsget_couponsDiscover available deals and couponscreate_orderInitialize a new orderadd_pizza_with_toppingsAdd customized pizzas with toppingsadd_item_to_orderAdd any menu itemview_orderPreview order details and pricingclear_orderClear current orderplace_orderAttempt to place orderget_ordering_guidanceAI-powered deal recommendationsTry it
Original README from dshanklin-bv/mcp-pizza
🍕 MCPizza - Enhanced
An educational MCP (Model Context Protocol) server demonstrating AI-powered pizza ordering with Domino's API integration.
⚠️ Important: This project is for educational purposes only. While it integrates with Domino's real API, actual order placement is blocked by CAPTCHA requirements. See Limitations for details.
Credits
This project is based on GrahamMcBain/mcpizza, with significant enhancements:
Original Project
- Author: Graham McBain
- Purpose: Educational MCP protocol demonstration
- Design: Safe-mode ordering without real placement
Our Enhancements
- ✅ Real API Integration - Actually calls Domino's pricing and validation APIs
- ✅ Pizza Customization -
add_pizza_with_toppingstool for proper coupon + topping configuration - ✅ Interaction Logging - Complete 2-way logging system for all MCP interactions
- ✅ Coupon Discovery -
get_couponsandget_ordering_guidancetools - ✅ Enhanced Error Handling - Detailed error reporting and validation
- ✅ Comprehensive Documentation - WORKFLOW.md with step-by-step instructions
What This Project Demonstrates
- MCP Protocol Integration - Full implementation of Model Context Protocol
- Real-world API Interaction - Integration with Domino's unofficial API
- Complex Tool Orchestration - 12 tools working together for multi-step workflows
- State Management - Order state management across tool calls
- Error Handling - Graceful handling of API validation and errors
Features
Store & Menu Tools
- 📍
find_stores- Find nearby Domino's by address or zip - 🏪
get_store_info- Detailed store information and hours - 📋
get_menu- Complete menu with categories - 🔍
search_menu- Search for specific items - 🎉
get_coupons- Discover available deals and coupons
Ordering Tools
- 📝
create_order- Initialize a new order - 🍕
add_pizza_with_toppings- Add customized pizzas with toppings (NEW!) - ➕
add_item_to_order- Add any menu item - 👁️
view_order- Preview order details and pricing - 🗑️
clear_order- Clear current order - 💳
place_order- Attempt to place order (blocked by CAPTCHA)
Guidance Tools
- 🎯
get_ordering_guidance- AI-powered deal recommendations (NEW!)
Installation
Prerequisites
- Python 3.10+
- uv package manager
Setup
# Clone the repository
git clone https://github.com/dshanklin-bv/mcp-pizza.git
cd mcp-pizza
# Install dependencies
uv pip install -e .
Claude Desktop Integration
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"pizza": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-pizza",
"run",
"mcpizza"
]
}
}
}
Usage
See WORKFLOW.md for complete ordering workflow documentation.
Basic Example
1. Find stores: "find pizza stores near 76104"
2. Get coupons: "what deals are available at store 8022?"
3. Get guidance: "I want a deep dish sausage and pepperoni pizza"
4. Create order: Create order with your details
5. Add pizza: Use add_pizza_with_toppings with coupon code
6. View order: Review pricing and details
7. (Optional) Place order: Will be blocked by CAPTCHA
Architecture
The codebase follows a clean, modular architecture with separation of concerns:
mcp-pizza/
├── mcpizza/
│ ├── server.py # Main MCP server (303 lines, down from 1308!)
│ ├── logger.py # Interaction logging system
│ ├── __main__.py # Entry point
│ │
│ ├── models/ # Pydantic parameter models
│ │ └── params.py # Tool parameter definitions
│ │
│ ├── services/ # Business logic layer
│ │ ├── store_service.py # Store lookup & menu browsing
│ │ ├── order_service.py # Order creation & management
│ │ ├── payment_service.py # Payment processing
│ │ └── guidance_service.py # AI ordering guidance
│ │
│ ├── tools/ # MCP tool handlers
│ │ ├── store_tools.py # Store-related tools
│ │ ├── menu_tools.py # Menu-related tools
│ │ ├── order_tools.py # Order-related tools
│ │ └── guidance_tools.py # Guidance tools
│ │
│ ├── api/ # Domino's API client
│ │ ├── endpoints.py # API endpoint constants
│ │ └── client.py # HTTP client wrapper
│ │
│ └── utils/ # Utilities
│ └── mock_order.py # Mock order object creation
│
├── tests/ # Comprehensive test suite (18 tests)
│ ├── test_models.py # Model validation tests
│ ├── test_utils.py # Utility function tests
│ ├── test_api_client.py # API client tests
│ └── test_services.py # Service layer tests
│
├── examples/ # Example scripts
│ └── test_mcp_with_ollama.p