MCP Travel Concierge Server

MCP Travel Concierge Server

Enables comprehensive travel planning by integrating Google Travel Services and Amadeus GDS for dual flight and hotel searches, plus event discovery, weather forecasting, currency conversion, and location services. Combines consumer-friendly search with professional travel industry data for optimal trip planning.

Category
访问服务器

README

🌟 MCP Travel Concierge Server

The Ultimate AI Travel Planning Assistant - A comprehensive MCP (Model Context Protocol) server that combines the best of Google Travel Services with Amadeus Professional Systems.

🚀 Overview

This Travel Concierge Server integrates two powerful travel platforms into one comprehensive solution:

  • 🌐 Google Travel Services (via SerpAPI) - Consumer-friendly search across flights, hotels, and events
  • 🏢 Amadeus Global Distribution System - Professional travel industry inventory and pricing

<div> <a href="https://www.loom.com/share/f865f975724b441fb31d88e20aa23067"> <p>MCP AI TRAVEL ASSISTANT - Watch Video</p> </a> <a href="https://www.loom.com/share/f865f975724b441fb31d88e20aa23067"> <img style="max-width:300px;" src="https://cdn.loom.com/sessions/thumbnails/f865f975724b441fb31d88e20aa23067-488994d5a959c3ff-full-play.gif"> </a> </div>

Get the best of both worlds: consumer accessibility with professional depth!

✨ Key Features

✈️ Dual Flight Search

  • Google Flights: Consumer-friendly pricing, popular routes, price insights
  • Amadeus GDS: Professional airline inventory, detailed fare classes, real-time availability

🏨 Comprehensive Hotel Search

  • Google Hotels: Vacation rentals, boutique properties, consumer reviews
  • Amadeus Hotels: Professional rates, real-time availability, business travel optimization

🎭 Complete Event & Activity Discovery

  • Google Events: Local festivals, concerts, cultural events
  • Amadeus Activities: Professional tours, curated experiences, verified operators

🌍 Additional Services

  • Geocoding & Distance Calculation: Precise location services
  • Weather Intelligence: Real-time conditions and forecasts
  • Currency Conversion: Live exchange rates
  • Financial Tracking: Travel industry stock monitoring

🛠️ Installation & Setup

1. Clone and Install Dependencies

# Clone the repository
git clone https://github.com/your-username/mcp_travelassistant.git
cd mcp_travelassistant

# Install dependencies
pip install -r requirements.txt

2. Set Up Environment Variables

Create a .env file in the project root with your API keys:

# Copy the example environment file
cp env.example .env

Edit the .env file with your actual API keys:

# Required API Keys
SERPAPI_KEY=your_serpapi_key_here
AMADEUS_API_KEY=your_amadeus_api_key_here
AMADEUS_API_SECRET=your_amadeus_api_secret_here
EXCHANGE_RATE_API_KEY=your_exchange_rate_api_key_here

Where to get API keys:

3. Run the Server

python travel_server.py

🔧 MCP Configuration

For Claude Desktop

Add this configuration to your Claude Desktop config file (usually located at ~/.cursor/mcp.json or ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "travel-concierge": {
      "command": "python",
      "args": ["combined_travel_server.py"],
      "cwd": "/path/to/your/mcp_travelassistant",
      "env": {
        "SERPAPI_KEY": "your_serpapi_key_here",
        "AMADEUS_API_KEY": "your_amadeus_api_key_here", 
        "AMADEUS_API_SECRET": "your_amadeus_api_secret_here",
        "EXCHANGE_RATE_API_KEY": "your_exchange_rate_api_key_here"
      }
    }
  }
}

For UV Package Manager

If you're using UV, you can use this configuration:

{
  "mcpServers": {
    "travel-concierge": {
      "command": "uv",
      "args": [
        "--directory", "/path/to/your/mcp_travelassistant/",
        "run", "python", "combined_travel_server.py"
      ],
      "env": {
        "SERPAPI_KEY": "your_serpapi_key_here",
        "AMADEUS_API_KEY": "your_amadeus_api_key_here",
        "AMADEUS_API_SECRET": "your_amadeus_api_secret_here", 
        "EXCHANGE_RATE_API_KEY": "your_exchange_rate_api_key_here"
      }
    }
  }
}

For HTTP Mode

If you prefer running the server in HTTP mode:

{
  "mcpServers": {
    "travel-concierge": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/client-http",
        "http://localhost:8000/"
      ]
    }
  }
}

Then run the server with: python travel_server.py --transport http --port 8000

🎯 Available Tools

✈️ Flight Search Tools

Tool Provider Description
search_flights_serpapi() Google Flights Consumer flight search with price insights
search_flights_amadeus() Amadeus GDS Professional airline inventory and fares

🏨 Hotel Search Tools

Tool Provider Description
search_hotels_serpapi() Google Hotels Consumer hotel search with reviews
search_hotels_amadeus_by_city() Amadeus GDS Professional city-based hotel search
search_hotels_amadeus_by_geocode() Amadeus GDS Professional coordinate-based search
search_hotel_offers_amadeus() Amadeus GDS Real-time hotel availability and pricing

🎭 Event & Activity Tools

Tool Provider Description
search_events_serpapi() Google Events Local events and cultural experiences
search_activities_amadeus() Amadeus GDS Professional tours and activities

🌍 Utility Tools

Tool Provider Description
geocode_location() Nominatim Convert addresses to coordinates
calculate_distance() Geopy Calculate distances between locations
get_weather_forecast() Open-Meteo Weather forecasts for travel planning
get_current_conditions() Open-Meteo Real-time weather conditions
convert_currency() ExchangeRate-API Live currency conversion
lookup_stock() Google Finance Travel industry stock tracking

🎨 Usage Examples

Comprehensive Trip Planning

# Search for flights from multiple providers
google_flights = search_flights_serpapi(
    departure_id="JFK",
    arrival_id="CDG", 
    outbound_date="2025-06-15",
    return_date="2025-06-22",
    adults=2
)

amadeus_flights = search_flights_amadeus(
    originLocationCode="JFK",
    destinationLocationCode="CDG",
    departureDate="2025-06-15",
    returnDate="2025-06-22",
    adults=2
)

Hotel Search Strategy

# Get coordinates first
location = geocode_location("Paris city center")

# Consumer search via Google Hotels
google_hotels = search_hotels_serpapi(
    location="Paris city center",
    check_in_date="2025-06-15", 
    check_out_date="2025-06-22"
)

# Professional search via Amadeus
amadeus_hotels = search_hotel_offers_amadeus(
    cityCode="PAR",
    checkInDate="2025-06-15",
    checkOutDate="2025-06-22"
)

Complete Trip Planning

# 1. Get destination coordinates
coords = geocode_location("Paris, France")

# 2. Check weather
weather = get_weather_forecast(
    latitude=coords['latitude'],
    longitude=coords['longitude']
)

# 3. Find events
events = search_events_serpapi(
    query="concerts museums",
    location="Paris",
    date_filter="week"
)

# 4. Convert currency for budget planning
budget_eur = convert_currency(
    from_currency="USD",
    to_currency="EUR", 
    amount=2000
)

🌟 Best Practices

1. Dual Search Strategy

Always search both platforms for flights and hotels to ensure you get the best deals and comprehensive options.

2. Location First

Start with geocode_location() to get precise coordinates, then use those for location-based searches.

3. Weather Integration

Check weather forecasts before finalizing activity plans using get_weather_forecast().

4. Currency Planning

Use convert_currency() for accurate international travel budgeting.

🔄 Docker Support

Build and Run

# Build the Docker image
docker build -t travel-concierge .

# Run with environment variables
docker run -p 8000:8000 \
  -e SERPAPI_KEY=your_key \
  -e AMADEUS_API_KEY=your_key \
  -e AMADEUS_API_SECRET=your_secret \
  -e EXCHANGE_RATE_API_KEY=your_key \
  travel-concierge

Docker Compose

# Copy environment file
cp env.example .env

# Edit .env with your API keys
# Then run:
docker-compose up

🐛 Troubleshooting

Common Issues

  1. Missing API Keys

    Error: SERPAPI_KEY environment variable is required
    

    Solution: Set your API keys in the .env file or environment variables

  2. Port Already in Use

    Error: Port 8000 is already in use
    

    Solution: Use a different port with --port 8001

  3. Amadeus Authentication Error

    Error: Invalid API credentials
    

    Solution: Verify your Amadeus API key and secret are correct

Health Check

When running in HTTP mode, visit http://localhost:8000/health to verify the server is running properly.

📈 Performance

  • Unified Architecture: Single server reduces overhead and complexity
  • Concurrent Requests: Handles multiple simultaneous requests efficiently
  • Rate Limiting: Built-in rate limiting for external API calls
  • Error Handling: Comprehensive error handling and recovery

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Make your changes
  4. Add tests if applicable
  5. Commit your changes (git commit -m 'Add some amazing feature')
  6. Push to the branch (git push origin feature/amazing-feature)
  7. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

  • Amadeus for Developers - Professional travel industry data
  • SerpAPI - Google Services integration
  • Open-Meteo - Weather data services
  • ExchangeRate-API - Currency conversion services
  • Nominatim/OpenStreetMap - Geocoding services

🆘 Support

For support, please:

  1. Check the documentation above
  2. Review the example environment file
  3. Open an issue with detailed information about your problem

Happy Travels! ✈️🏨🎭🌍

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