MCPizza - Enhanced MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
git clone https://github.com/dshanklin-bv/mcp-pizza.git
cd mcp-pizza
uv pip install -e .
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add mcp-pizza -- node "<FULL_PATH_TO_MCP_PIZZA>/dist/index.js"

Replace <FULL_PATH_TO_MCP_PIZZA>/dist/index.js with the actual folder you prepared in step 1.

README.md

An educational MCP server demonstrating AI-powered pizza ordering

šŸ• MCPizza - Enhanced

An educational MCP (Model Context Protocol) server demonstrating AI-powered pizza ordering with Domino's API integration.

āš ļø 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

  • āœ… Real API Integration - Actually calls Domino's pricing and validation APIs
  • āœ… Pizza Customization - add_pizza_with_toppings tool for proper coupon + topping configuration
  • āœ… Interaction Logging - Complete 2-way logging system for all MCP interactions
  • āœ… Coupon Discovery - get_coupons and get_ordering_guidance tools
  • āœ… Enhanced Error Handling - Detailed error reporting and validation
  • āœ… Comprehensive Documentation - WORKFLOW.md with step-by-step instructions

What This Project Demonstrates

  1. MCP Protocol Integration - Full implementation of Model Context Protocol
  2. Real-world API Interaction - Integration with Domino's unofficial API
  3. Complex Tool Orchestration - 12 tools working together for multi-step workflows
  4. State Management - Order state management across tool calls
  5. Error Handling - Graceful handling of API validation and errors

Features

Store & Menu Tools

  • šŸ“ find_stores - Find nearby Domino's by address or zip
  • šŸŖ get_store_info - Detailed store information and hours
  • šŸ“‹ get_menu - Complete menu with categories
  • šŸ” search_menu - Search for specific items
  • šŸŽ‰ get_coupons - Discover available deals and coupons

Ordering Tools

  • šŸ“ create_order - Initialize a new order
  • šŸ• add_pizza_with_toppings - Add customized pizzas with toppings (NEW!)
  • āž• add_item_to_order - Add any menu item
  • šŸ‘ļø view_order - Preview order details and pricing
  • šŸ—‘ļø clear_order - Clear current order
  • šŸ’³ place_order - Attempt to place order (blocked by CAPTCHA)

Guidance Tools

  • šŸŽÆ 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/
ā”œā”€ā”€ mcpizza/
│   ā”œā”€ā”€ server.py          # Main MCP server (303 lines, down from 1308!)
│   ā”œā”€ā”€ logger.py          # Interaction logging system
│   ā”œā”€ā”€ __main__.py        # Entry point
│   │
│   ā”œā”€ā”€ models/            # Pydantic parameter models
│   │   └── params.py      # Tool parameter definitions
│   │
│   ā”œā”€ā”€ services/          # Business logic layer
│   │   ā”œā”€ā”€ store_service.py     # Store lookup & menu browsing
│   │   ā”œā”€ā”€ order_service.py     # Order creation & management
│   │   ā”œā”€ā”€ payment_service.py   # Payment processing
│   │   └── guidance_service.py  # AI ordering guidance
│   │
│   ā”œā”€ā”€ tools/             # MCP tool handlers
│   │   ā”œā”€ā”€ store_tools.py       # Store-related tools
│   │   ā”œā”€ā”€ menu_tools.py        # Menu-related tools
│   │   ā”œā”€ā”€ order_tools.py       # Order-related tools
│   │   └── guidance_tools.py    # Guidance tools
│   │
│   ā”œā”€ā”€ api/               # Domino's API client
│   │   ā”œā”€ā”€ endpoints.py         # API endpoint constants
│   │   └── client.py            # HTTP client wrapper
│   │
│   └── utils/             # Utilities
│       └── mock_order.py        # Mock order object creation
│
ā”œā”€ā”€ tests/                 # Comprehensive test suite (18 tests)
│   ā”œā”€ā”€ test_models.py     # Model validation tests
│   ā”œā”€ā”€ test_utils.py      # Utility function tests
│   ā”œā”€ā”€ test_api_client.py # API client tests
│   └── test_services.py   # Service layer tests
│
ā”œā”€ā”€ examples/              # Example scripts
│   └── test_mcp_with_ollama.p

Tools (12)

find_storesFind nearby Domino's by address or zip
get_store_infoDetailed store information and hours
get_menuComplete menu with categories
search_menuSearch for specific items
get_couponsDiscover available deals and coupons
create_orderInitialize a new order
add_pizza_with_toppingsAdd customized pizzas with toppings
add_item_to_orderAdd any menu item
view_orderPreview order details and pricing
clear_orderClear current order
place_orderAttempt to place order
get_ordering_guidanceAI-powered deal recommendations

Configuration

claude_desktop_config.json
{"mcpServers": {"pizza": {"command": "uv", "args": ["--directory", "/path/to/mcp-pizza", "run", "mcpizza"]}}}

Try it

→Find pizza stores near 76104
→What deals are available at store 8022?
→I want a deep dish sausage and pepperoni pizza
→Create a new order for store 8022 and add a large pepperoni pizza
→View my current order details and pricing

Frequently Asked Questions

What are the key features of MCPizza - Enhanced?

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.

What can I use MCPizza - Enhanced for?

Learning how to implement complex tool orchestration in MCP. Testing AI-driven interaction with unofficial third-party APIs. Exploring state management patterns for multi-step ordering workflows.

How do I install MCPizza - Enhanced?

Install MCPizza - Enhanced by running: git clone https://github.com/dshanklin-bv/mcp-pizza.git && cd mcp-pizza && uv pip install -e .

What MCP clients work with MCPizza - Enhanced?

MCPizza - Enhanced works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep MCPizza - Enhanced docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare