Rakuten Travel
Search for hotels and check their availability using the Rakuten Travel API.
Rakuten Travel MCP Server
A Model Context Protocol (MCP) server that provides an interface to the Rakuten Travel API for hotel searching and availability checking.
Features
- Hotel Search: Search for hotels by location, hotel number, or area code
- Availability Search: Find vacant hotels with real-time availability
- Area Code Resource: Access hierarchical Japanese location data
- Type-Safe: Comprehensive TypeScript types with Zod validation
- MCP Compliant: Works with any MCP-compatible client
Prerequisites
- Deno runtime installed
- Rakuten Travel API Application ID (Get one here)
Installation
- Clone the repository:
git clone https://github.com/yourusername/rakuten_travel_mcp.git
cd rakuten_travel_mcp
Usage
Running the Server
- configure your MCP client. (following example is for
Claude Desktop)
```json
{
"mcpServers": {
"rakuten_travel_mcp": {
"command": "deno",
"args": [
"run",
"--allow-net=app.rakuten.co.jp",
"--allow-env=APPLICATION_ID",
"/path/to/rakuten_travel_mcp/serve.ts"
],
"env": {
"APPLICATION_ID": "<your_application_id>"
}
}
}
}
Available Tools
1. Hotel Search (hotel-search)
Search for hotels using various criteria:
Search by Hotel Number:
{
"hotelNo": ["123456", "789012"]
}
Search by Coordinates:
{
"latitude": 35.6762,
"longitude": 139.6503,
"searchRadius": 3,
"datumType": 1
}
Search by Area Code:
{
"largeClassCode": "japan",
"middleClassCode": "tokyo",
"smallClassCode": "shibuya"
}
2. Vacant Hotel Search (vacant-hotel-search)
Search for available hotels:
{
"checkinDate": "2024-03-15",
"checkoutDate": "2024-03-17",
"rooms": 1,
"adultNum": 2,
"largeClassCode": "japan",
"middleClassCode": "tokyo"
}
Available Resources
Area Code Resource (config://area_code)
Access hierarchical location data for Japan:
- Country level (e.g., "japan")
- Prefecture level (e.g., "tokyo", "osaka")
- City level (e.g., "shibuya", "shinjuku")
- Area level (detailed districts)
Development
Running Tests
# Run all tests
deno task test
# Run tests in watch mode
deno task test:watch
Project Structure
rakuten_travel_mcp/
├── serve.ts # Main MCP server implementation
├── types.ts # TypeScript types and Zod schemas
├── area_code.json # Hierarchical location data
├── *.test.ts # Test files
├── deno.json # Deno configuration
└── .env # Environment variables (create this)
API Parameters
Common Parameters
hits: Number of results per page (1-30, default: 30)page: Page number for paginationsort: Sort order (various options available)
Hotel Search Specific
hotelNo: Array of hotel numberslatitude/longitude: Coordinates for geographic searchsearchRadius: Search radius in km (1-3)squeezeCondition: Filter for hotels with/without vacancieshotelType: Filter by hotel type (0-3)
Vacant Hotel Search Specific
checkinDate/checkoutDate: Required dates (YYYY-MM-DD)rooms: Number of rooms (1-5)adultNum: Adults per room (1-5)minCharge/maxCharge: Price range filters
Testing
The project includes comprehensive tests for:
- Schema validation
- API parameter building
- Response processing
- Error handling
- Network timeouts
Error Handling
The server handles various error scenarios:
- Missing required parameters
- Invalid date formats
- API rate limits
- Network timeouts
- Invalid API responses
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built with Model Context Protocol SDK
- Powered by Rakuten Travel API
Related Servers
News Fact-Checker
Automated fact-checking of news headlines using web search and Google Gemini AI.
Amadeus MCP Server
Search for flight offers using the Amadeus Flight Offers Search API.
Qdrant MCP Server
Semantic code search using the Qdrant vector database and OpenAI embeddings.
Pearch
Best people search engine that reduces the time spent on talent discovery.
YaCy MCP Server
MCP (Model Context Protocol) Server implementation that provides AI tools to search using YaCy web search API.
IP2Location.io
IP2Location.io API integration to retrieve the geolocation information for an IP address.
Greenbook
A lightweight Model Context Protocol (MCP) server that exposes Greenbook data and tools for market research professionals, analysts, and related workflows.
Perplexity Ask MCP Server
A connector for the Perplexity API to enable web search within the MCP ecosystem.
Legislative Yuan API
Search for bills, documents, and meeting records from Taiwan's Legislative Yuan API.
Library Docs MCP Server
Search and fetch documentation for popular libraries like Langchain, Llama-Index, and OpenAI using the Serper API.