Master Control Program (MCP) Backend

Master Control Program (MCP) Backend

Provides API endpoints for a hotel management frontend and integrates with SmartThings API to control devices based on user preferences and room assignments.

Category
访问服务器

README

Samsung SmartThings Hotel Integration Demo

This is a demonstration of the integration between Samsung SmartThings and a hotel booking system, allowing personalized temperature settings based on user preferences.

Overview

The demo consists of:

  1. A Streamlit Frontend for hotel staff and management to:

    • Manage users and their temperature preferences
    • Manage hotel rooms
    • Create and manage bookings
    • Assign rooms and check out guests
    • View a dashboard of hotel stats and SmartThings integration status
    • Use an AI chatbot interface to interact with the system
  2. An MCP (Master Control Program) Backend which:

    • Provides API endpoints for the frontend
    • Integrates with SmartThings API for device control
    • Manages user preferences, room assignments, and bookings

Project Structure

├── app.py                  # Main Streamlit application
├── mcp/                    # MCP backend
│   ├── server.py           # FastAPI server
│   ├── smartthings.py      # SmartThings API integration
├── utils/                  # Utility modules
│   ├── database.py         # Local database operations
├── data/                   # Data storage (created at runtime)
│   ├── users.json
│   ├── rooms.json
│   ├── bookings.json
├── README.md               # This file

Setup and Installation

Prerequisites

  • Python 3.8 or higher
  • pip package manager

Installation Steps

  1. Clone this repository:

    git clone <repository-url>
    cd mcpSmartThings
    
  2. Install required dependencies:

    pip install streamlit fastapi uvicorn pydantic pandas torch transformers
    

Running the Demo

Start the MCP Backend Server

  1. Start the MCP backend server:

    cd mcpSmartThings
    python -m mcp.server
    

    The MCP server will start on http://localhost:8000

  2. In a new terminal, start the Streamlit frontend:

    cd mcpSmartThings
    streamlit run app.py
    

    The Streamlit app will open in your browser at http://localhost:8501

Using the Demo

  1. Load Sample Data:

    • Go to the sidebar and click "Load Sample Data" to populate the system with sample users, rooms, and bookings.
  2. Users Tab:

    • Create new users with their temperature preferences
    • Update existing user temperature preferences
  3. Rooms Tab:

    • Add new hotel rooms
    • Set room temperatures manually
  4. Bookings Tab:

    • Create new bookings for users
    • Assign rooms to bookings (check-in)
    • Process checkouts
  5. Dashboard Tab:

    • View hotel statistics
    • Monitor room temperatures
    • Check SmartThings integration status
  6. Claude Interface Tab:

    • Enable the local LLM option to use TinyLlama for AI responses
    • Chat with the assistant to book rooms or set temperature preferences
    • Experience a conversational interface to the hotel system

SmartThings Integration

The SmartThings integration is simulated in this demo. In a real-world implementation, it would connect to the actual SmartThings API to control:

  • Room temperature (AC/heating)
  • Room lighting
  • Door locks
  • Other smart devices

When a guest checks in, their preferred temperature (saved in their profile) is automatically applied to their assigned room through SmartThings.

API Documentation

Once the MCP server is running, you can access the API documentation at: http://localhost:8000/docs

This provides an interactive interface to explore and test all available API endpoints.

Troubleshooting

  • If you encounter issues with the TinyLlama model loading, you can disable the "Use Local LLM" toggle in the Claude Interface tab to use the basic pattern matching implementation instead.
  • If the MCP server isn't connecting, check the URL in the Streamlit app sidebar (default is http://localhost:8000).
  • Data is stored in JSON files in the data directory. You can reset the data by clicking "Reset Demo Data" in the sidebar.

Credits

This demonstration was created by Samsung for illustrating the potential of SmartThings integration with hotel management systems.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选