mcpField
R
Rollinggo Hotel Mcp

Rollinggo Hotel Mcp

Remote
github.com/longcreatMaps & Travel2Updated 33w ago
Repository

About Rollinggo Hotel Mcp

AigoHotel MCP Server lets AI assistants search hotels worldwide, with filters for destination type, dates, rating, and distance. Results include hotel details and location information.

Key features

  1. 01Search by city, attraction, and more
  2. 02Filter by dates, rating, and distance
  3. 03Return hotel details and locations

Use cases

  1. 01Find lodging in a city
  2. 02Search for highly rated hotels near attractions

MCP support

The MCP server exposes hotel search through the search_hotels tool. It supports streamable-http transport and requires an API key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.rollinggo.cn/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://mcp.rollinggo.cn/mcpAuth required

Tools

Details

From the project README

AigoHotel MCP Server

License: MIT Python 3.8+ FastMCP

AIGOHOTEL 酒店搜索 MCP Server。通过标准的 Model Context Protocol (MCP) 协议为 AI 助手提供全球酒店搜索能力。

工具列表

search_hotels - 查询全球酒店信息

  • 支持按城市、景点、酒店、交通枢纽等多种地点类型搜索
  • 支持星级筛选、距离筛选、入住日期等多维度条件
  • 返回符合条件的酒店列表(JSON格式)
请求参数

必填参数:

  • place (string): 目的地(城市、景点、酒店、交通枢纽、地标等)
  • placeType (string): 目的地类型(城市、区/县、机场、火车站、酒店、景点等)

可选参数:

  • originalQuery (string): 用户的原始问询句
  • checkIn (string): 入住日期,格式 yyyy-MM-dd,默认次日
  • stayNights (int): 入住晚数,默认 1
  • starRatings (array): 酒店星级范围,如 [4.5, 5.0],默认 [0.0, 5.0]
  • adultCount (int): 每间房成人数量,默认 2
  • distanceInMeter (int): 距离景点的米数,默认 5000
  • size (int): 返回结果数量,默认 10,最大 20
  • withHotelAmenities (bool): 是否包含酒店设施,默认 true
  • withRoomAmenities (bool): 是否包含客房设施,默认 true
  • language (string): 语言环境(zh_CN, en_US等),默认 zh_CN
  • queryParsing (bool): 是否分析用户个性化需求,默认 true
返回参数
{
  "hotelId": "酒店ID",
  "name": "酒店名称",
  "address": "酒店位置",
  "destinationId": "目的地",
  "latitude": 30.665025, # 纬度
  "longitude": 104.066475, # 经度
  "starRating": 5.0, # 星级
  "bookingUrl": "酒店预定详情页",
  "description": "酒店描述",
  "imageUrl": "酒店首图",
  "areaCode": "国家",
  "price": 549.0, # 价格
  "hotelAmenities": [
    "咖啡厅咖啡厅",
    "会议厅会议室",
    // ... 部分省略
  ], # 酒店设施
  "hotelRoomAmenities": [], # 房间设施
  "tags": [], # 酒店个性化标签
  "score": "个性化评分",
  "currency": "CNY" # 币种
}

使用示例

示例 1: 搜索西雅图的酒店

{
  "place": "西雅图",
  "placeType": "城市"
}

示例 2: 搜索白金汉宫附近的高星级酒店

{
  "place": "白金汉宫",
  "placeType": "景点",
  "checkIn": "2026-01-01",
  "starRatings": [4.5, 5.0]
}

配置方法

目前仅支持streamable-http 传输

1. 安装依赖
# 创建虚拟环境
python -m venv venv

# 激活虚拟环境
# Windows:
venv\Scripts\activate
# Linux/Mac:
source venv/bin/activate

# 安装依赖包
pip install -r requirements.txt
2. 配置 API Key (必需)

获取 API Key: https://mcp.agentichotel.cn/apply

# Windows (复制文件)
copy .env.example .env

# Linux/Mac (复制文件)
cp .env.example .env

编辑 .env 文件,填入你的 API Key:

AIGOHOTEL_API_KEY=mcp_your_actual_api_key_here

重要:

3. 启动服务器
python server.py

启动成功后会显示:

AigoHotel MCP Server 启动中...
MCP 端点: http://0.0.0.0:8000/mcp (默认)
API Key: 已配置
INFO: Uvicorn running on http://127.0.0.1:8000

如果 API Key 格式错误,会显示警告:

警告: API Key 格式错误,应以 'mcp_' 开头

MCP 客户端配置

在 MCP 配置文件中添加以下内容:

{
  "mcpServers": {
    "aigohotel": {
      "url": "http://localhost:8000/mcp"
    }
  }
}

API 鉴权说明

申请 API Key

访问 https://mcp.agentichotel.cn/apply 申请 API Key

许可证

本项目采用 MIT 许可证 - 查看 LICENSE 文件了解详情。

相关链接

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.