Restaurant Backend MCP Server
Enables interaction with a restaurant FastAPI backend for menu management, order processing, customer management, and analytics through natural language.
README
Restaurant Backend MCP Server
MCP (Model Context Protocol) server for interacting with the Restaurant FastAPI backend.
Installation
cd mcp-servers/backend-mcp
uv sync
Configuration
Update the BASE_URL in src/backend_mcp/server.py to match your FastAPI backend URL:
(python)
BASE_URL = "http://localhost:8000" # Change this to your backend URL
Available Tools
Menu Management
- get_menu_items - Browse menu items with filters
- get_menu_item_details - Get detailed item information
- create_menu_item - Add new menu items (staff only)
- update_menu_item - Update existing items (staff only)
Order Management
- create_order - Place new orders
- get_order_details - Get order information
- get_customer_orders - Get all orders for a customer
- get_orders_by_status - Filter orders by status
- update_order_status - Update order status
- get_order_journey - View order status history
- get_filtered_orders - Advanced order filtering
Customer Management
- register_customer - Create new customer account
- get_customer_profile - Get customer information
- update_customer_profile - Update customer details
- customer_login - Authenticate customer
Promo Codes
- apply_promo_code - Validate and calculate discounts
- get_promo_details - Get promo code information
Reviews
- get_order_reviews - Get order reviews
- create_review - Submit a review
Analytics
- get_dashboard_stats - Overall statistics
- get_popular_items - Most ordered items
- get_revenue_stats - Revenue analysis
Staff Operations
- staff_login - Staff authentication
System
- check_backend_health - Backend health check
Running the Server
For Development/Testing
uv run python -m backend_mcp.server
As MCP Server (for Claude Desktop)
Add to your Claude Desktop config:
(.json)
{
"mcpServers": {
"restaurant-backend": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-servers/backend-mcp",
"run",
"backend-mcp"
]
}
}
}
Testing
uv run python test_server.py
**Make sure your FastAPI backend is running before testing.
Environment Variables
You can override the backend URL using environment variables:
export BACKEND_URL="http://<your-backend-url>:8000"
Architecture
Chatbot (Claude)
↓ (MCP Protocol)
Backend MCP Server
↓ (HTTP/REST)
FastAPI Backend
↓
Database
Next
- Create Database MCP Server for direct SQL operations Implement authentication/authorization
- Add error handling and retry logic
- Add caching for frequently accessed data
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。