azure-samples/pizza-mcp-agents

⭐ 如果你喜欢这个样本，请在GitHub上点星——这对你帮助很大！

概述 • 入门 • 本地开发 • 部署到 Azure • 资源 • 故障排除

该项目演示如何利用**模型上下文协议（MCP）**构建能够与现实世界API交互的AI代理。它配备了完整的披萨点餐系统，配备无服务器API、网页界面和MCP服务器，使AI代理能够浏览菜单、下单并跟踪订单状态。

该系统由多个互联服务组成：

• Pizza API：无服务器的披萨订购API
• Pizza MCP 服务器：支持 AI 代理交互的 MCP 服务器
• 披萨网页应用：实时订单仪表盘，实时显示披萨订单状态
• 注册系统：用户注册以访问披萨订购系统

[!提示] 你可以在本地测试该应用，无需部署或任何云端成本。MCP服务器可与GitHub Copilot、Claude及其他兼容MCP的客户端等流行的AI工具配合使用。

概述

本示例使用了在Azure上部署的微服务架构：

核心组件

This project demonstrates how to build AI agents that can interact with real-world APIs using the Model Context Protocol (MCP). It features a complete pizza ordering system with a serverless API, web interfaces, and an MCP server that enables AI agents to browse menus, place orders, and track order status.

The system consists of multiple interconnected services:

• Pizza API: Serverless API for pizza ordering
• Pizza MCP server: MCP server enabling AI agent interactions
• Pizza web app: Live order dashboard, showing real-time pizza orders status
• Registration system: User registration for accessing the pizza ordering system

[!TIP] You can test this application locally without deployment needed or any cloud costs. The MCP server works with popular AI tools like GitHub Copilot, Claude, and other MCP-compatible clients.

Overview

This sample uses a microservices architecture deployed on Azure:

Core components

• Pizza API (Azure Functions): RESTful API handling pizza menu, orders, and business logic
• Pizza MCP server (Azure Container Apps): Exposes the pizza API through MCP, enabling AI agents to interact with the pizza ordering system
• Pizza web app (Azure Static Web Apps): Real-time dashboard for monitoring orders and system status