Skip to main content

国内景点智能推荐MCP Server - 景点搜索/门票价格/购票链接/5A景区筛选

Project description

国内景点智能推荐 MCP Server

这是一个专注国内景点门票的智能推荐MCP服务,为AI助手、旅行智能体及Cursor/Cherry Studio/Windsurf等IDE提供覆盖全国范围的景点搜索、门票价格查询与购票链接生成能力,满足各类景点查询与出行规划需求。该服务支持通过城市名称、景点关键词等多种方式进行精准搜索,并提供灵活的景区等级筛选(5A/4A/3A)、景点类型分类等专业筛选功能。此外,服务返回景点介绍、评分、门票价格及可直接购票的官方链接等结构化数据,支持按关键词快速定位目标景点。整个服务通过标准MCP协议交互,智能完成从城市解析、景点筛选、门票查询到购票链接生成的完整服务流程,为旅行智能体搭建、AI编程助手集成及对话式旅行应用提供精准、高效的国内景点检索与购票解决方案。

工具列表

search_poi - 景点门票搜索

搜索国内景点,返回门票价格和购票链接。支持按城市、关键词、景区等级筛选。

参数:

  • city(必填):城市,如"深圳""杭州""北京"
  • keyword:景点关键词,如:西湖、长城、迪士尼
  • category:景点类型
  • level:景区等级 1-5(5=5A级景区)
  • limit:返回数量,默认10

安装

pip install mcp-poi-smart-recommend

或使用 uvx 直接运行:

uvx mcp-poi-smart-recommend

配置

支持以下环境变量(托管部署时由平台自动配置,无需手动设置):

变量名 说明 是否必填
HOTEL_API_KEY 服务接口密钥 选填
HOTEL_SIGN_SECRET 服务签名密钥 选填

在 MCP 客户端中配置

{
  "mcpServers": {
    "poi-smart-recommend": {
      "command": "uvx",
      "args": ["mcp-poi-smart-recommend"],
      "env": {}
    }
  }
}

适用场景

  • AI编程助手:在Cursor/Windsurf中直接调用景点搜索,为旅行规划项目提供数据
  • 旅行智能体:给旅行AI Agent接上景点能力,实现"推荐景点→查门票→给链接"闭环
  • 对话式旅行应用:低延迟响应,适配实时对话场景
  • 与酒店服务联动:搭配酒店MCP服务,构建"住+玩"一站式旅行方案

技术特性

  • 基于MCP(Model Context Protocol)标准
  • 支持景区等级筛选(5A/4A/3A)
  • 返回结构化数据:景点介绍、评分、门票价格、购票链接
  • SSE流式响应支持

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_poi_smart_recommend-1.0.1.tar.gz (11.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_poi_smart_recommend-1.0.1-py3-none-any.whl (6.6 kB view details)

Uploaded Python 3

File details

Details for the file mcp_poi_smart_recommend-1.0.1.tar.gz.

File metadata

  • Download URL: mcp_poi_smart_recommend-1.0.1.tar.gz
  • Upload date:
  • Size: 11.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.12

File hashes

Hashes for mcp_poi_smart_recommend-1.0.1.tar.gz
Algorithm Hash digest
SHA256 0737051e43fbd5bb22a0e6b7b755b5bc6b2c98c381b682c95aca66a343940b24
MD5 bd6040bfb9ac5beba84da2682ec72bd4
BLAKE2b-256 4f3992ac343465877810004a63c7a84b3a64473bfa772cf240db8d043b3cdcc0

See more details on using hashes here.

File details

Details for the file mcp_poi_smart_recommend-1.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_poi_smart_recommend-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ba8a7eb3bc17912c91a57c7269282bb3b1af3dd9493c28e78fbebdba6ca7fb7f
MD5 11af337357789afd767a404c9fd1c501
BLAKE2b-256 8208ddf6816cce535afe0903c4b1a177db648d67c21f0fb02a4e7beb7bbaa45f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page