RollingGo Hotel MCP — Hotel Search & Booking

🏠 Apply Key · 🚀 Quick Start · 📚 Examples · 💬 Support · 🔍 Q&A · 💰Earn with RollingGo

This is an official MCP server empowers AI Agents to search, compare, and book over 2 Million hotels globally; this server bridges the gap between AI travel recommendations and real-world bookings.

• Transport Protocol: streamable-http
• Pricing: Completely free, no usage limits
• Access Method: Self-service following this documentation; suitable for rapid prototyping and tool development.

RollingGo MCP also offers an OAuth 2.0 Authorization Code flow, providing 7 tools including getHotelSearchTags, searchHotels, getHotelDetail, hotelPriceConfirm, searchHotelOrders, and more. This mode is designed for deep integration with enterprise-grade production applications and requires a business contact via contact@rollinggo.ai.

For Chinese users or workflows primarily targeting the mainland China market and Alipay payment systems, please refer to this version: RollingGo-hotel-MCP-CN

🌟 Why DIDA Hotel MCP?

Traditional AI agents can only recommend hotels based on static training datasets. The RollingGo Hotel MCP equips your LLM agent with direct, real-time transactional capabilities:

✅ Live Rates & Bookable Inventory — Zero-latency price verification; every result is instantly bookable.

✅ Supply Chain — Fully API-native end-to-end.

✅ Global Hotel Network — 2,000,000+ properties covering 200+ countries/regions. 500+ suppliers covering every tier, from luxury chains to local boutiques.

✅ Direct Contracts — 110,000+ directly connected hotels with live price and inventory sync.

✅ Price Edge at Source — Priced upstream of OTAs; sharp rates on hot spots.

✅ Agent-Ready — Works with 40+ leading agents: Cursor, Claude Code, Codex, Windsurf, Copilot, and more.

✅ Earn your Revenue on Every MCP Call — Set country-specific markups, earn commission on every completed booking, and track your orders, earnings, and payouts in real time. Flexible withdrawals for both businesses and individual developers.

🎯 Who is it for

• Companies or individual developers building AI Agents

• Developers looking to integrate hotel booking capabilities into MCP Clients

• Developers building travel planning, business travel management, OTA, and lifestyle service agents

• Product teams seeking to validate AI Agent commercial transaction loops

• Individuals with needs for hotel search, price comparison, and price drop alerts******

🎯 Use Cases

• General-Purpose Agents: Equip any AI agent with native hotel booking. Users can compare, filter, and book—all within a single natural-language conversation.
• AI Travel Planners: Integrate hotel searching directly into natural language itineraries.
• Corporate Travel Assistants: Allow employees to query, compare, and book business travel within Slack, Teams, or custom chat interfaces.
• Transactional Demos: Validate end-to-end AI agent commerce and payment flows without heavy backend integration.

🚀 Quick Start

Integrate global hotel search and booking into your AI assistant in under 5 minutes with no coding required.

Step 1: Get Your Developer API Key

1. Go to the DIDA Partner Center and sign up for a free key.
2. You will receive an email containing: Credentials for your B2B Partner Center dashboard (to monitor orders, configure markup, and track earnings).

Step 2: Connect to Your Agent

Recommended clients: Claude CLI, Codex, and Cursor. Other MCP-compatible clients (such as Kiro, Doubao, etc.) can be configured similarly.

Claude CLI

Create .mcp.json in your project root:

{
  "mcpServers": {
    "Dida-Hotel": {
      "url": "https://mcp.rollinggo.ai/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Or add directly via the command line:

claude mcp add \
  --transport http \
  --header "Authorization: Bearer YOUR_API_KEY" \
  Dida-Hotel \
  https://mcp.rollinggo.ai/mcp

Codex

Config file location: .codex/config.json in the project root, or globally at ~/.codex/config.json

{
  "mcpServers": {
    "Dida-Hotel": {
      "url": "https://mcp.rollinggo.ai/mcp",
      "type": "streamable-http",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Cursor

Config file location: .cursor/mcp.json in the project root, or globally at ~/.cursor/mcp.json

{
  "mcpServers": {
    "Dida-Hotel": {
      "url": "https://mcp.rollinggo.ai/mcp",
      "type": "streamable-http",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with your actual API Key.

Test Directly with cURL

Note: cURL must include -H "Accept: application/json, text/event-stream", otherwise the server will return a 400 error.

curl -X POST https://mcp.rollinggo.ai/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "searchHotels",
      "arguments": {
        "originQuery": "Shanghai Bund five-star hotel",
        "place": "Shanghai Bund",
        "placeType": "Attraction",
        "checkInParam": {
          "checkInDate": "2026-06-01",
          "stayNights": 2
        },
        "filterOptions": {
          "starRatings": [5.0]
        },
        "size": 3
      }
    },
    "id": 1
  }'

Step 3: Your First MCP Call

Once configured, simply tell your AI assistant:

"Find me a five-star hotel near the Shanghai Bund for a stay starting the day after tomorrow."

The AI will automatically call the searchHotels Tool and return a list of hotels.

Hotel Search Example

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "searchHotels",
    "arguments": {
      "originQuery": "Shanghai Bund five-star hotel",
      "place": "Shanghai Bund",
      "placeType": "Attraction",
      "checkInParam": {
        "checkInDate": "2026-06-01",
        "stayNights": 2
      },
      "filterOptions": {
        "starRatings": [5.0]
      },
      "size": 3
    }
  },
  "id": 1
}

Step 4: View Results and Sample Data

Hotel Search Results (Real Data)

Searching for "Shanghai Bund five-star hotel", 2 nights, returns:

Expected Response JSON Example

{
  "message": "Hotel search successful",
  "hotelInformationList": [
    {
      "hotelId": 29529,
      "bookingUrl": "https://rollinggo.ai/pages/hotel/detail/index?...",
      "name": "Fairmont Peace Hotel on the Bund",
      "address": "No. 20 Nanjing East Road",
      "starRating": 5.0,
      "price": {
        "message": "Price query successful. Lowest price: 648, Currency: USD",
        "hasPrice": true,
        "currency": "USD",
        "lowestPrice": 648.0
      },
      "hotelAmenities": ["Bar", "Gym", "Pool", "SPA", "Parking", "WIFI"],
      "tags": ["SPA Service", "Resort Hotel", "Sports-Friendly Hotel"]
    }
  ]
}

🔧 Available Tools

Official Docs | Dida MCP Tools

The server registers 3 core tools to handle the complete search-to-book lifecycle:

1) searchHotels

Find hotels by location, date, price, star rating, and tags.

• Input Parameters:
  • originQuery (string, required): User's raw text request (e.g., "Find boutique hotels in Tokyo under $200").
  • place (string, required): Specific destination, attraction, or airport name.
  • placeType (string, required): Location type (city, airport, point_of_interest, hotel, etc.). Supported values: city, airport, point_of_interest, train_station, subway_station, hotel, district/county, detailed address.
  • countryCode (string, optional): ISO 3166-1 alpha-2 country code, e.g. CN, US.
  • size (number, optional, default: 5): Number of hotels to return, max 20.
  • checkInParam (object, optional): Check-in related parameters.
  • filterOptions (object, optional): Filter parameters.
  • hotelTags (object, optional): Tag / brand / budget filters.