旅行搜索与预订 MCP Server
智能旅行服务:酒店推荐、万豪搜索、景点门票、旅行规划,返回真实价格和可预订/购票链接。
功能
- 酒店智能推荐 — 根据目的地、预算、星级等条件搜索酒店
- 万豪酒店搜索 — 搜索万豪集团旗下酒店(万豪/喜来登/JW/威斯汀/丽思卡尔顿/万丽/万枫等)
- 景点门票搜索 — 搜索景点,返回门票价格和购票链接,支持5A景区筛选
- 旅行规划 — 自然语言输入需求,AI生成完整旅行方案(酒店+景点+行程安排+预算分配)
安装
pip install mcp-travel-search
或使用 uvx 直接运行:
uvx mcp-travel-search
配置
需要设置以下环境变量:
| 变量名 | 说明 | 获取方式 |
|---|---|---|
| FLYAI_API_KEY | FlyAI API密钥 | https://flyai.open.fliggy.com 注册获取 |
| FLYAI_SIGN_SECRET | FlyAI签名密钥 | 同上 |
使用
在 MCP 客户端中配置
{
"mcpServers": {
"travel-search": {
"command": "uvx",
"args": ["mcp-travel-search"],
"env": {
"FLYAI_API_KEY": "你的API密钥",
"FLYAI_SIGN_SECRET": "你的签名密钥"
}
}
}
}
工具列表
search_hotels - 酒店智能推荐
根据目的地和条件搜索酒店,返回真实价格和可预订链接。
参数:
dest(必填):目的地,如"深圳""上海外滩"max_price:最高价格/晚hotel_stars:星级(5=豪华型/4=高档型/3=舒适型)checkin/checkout:入住/退房日期 YYYY-MM-DDpoi:附近景点/地标sort:排序(rate_desc/price_asc/price_desc/distance_asc)keywords:关键词limit:返回数量,默认10
示例:搜索深圳400元以内的高档型酒店
search_marriott_hotels - 万豪酒店搜索
搜索万豪集团旗下酒店,返回真实价格和可预订链接。
参数:
dest(必填):目的地max_price:最高价格/晚checkin/checkout:入住/退房日期sort:排序方式limit:返回数量,默认10
示例:搜索上海800元以内的万豪酒店
search_poi - 景点门票搜索
搜索景点,返回门票价格和购票链接。
参数:
city(必填):城市keyword:景点关键词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
示例:搜索北京的5A级景区
plan_travel - 旅行规划
根据自然语言需求智能规划旅行方案,涵盖酒店、景点、度假套餐和行程安排。
参数:
query(必填):自然语言旅行需求,如"三亚度蜜月预算1万怎么安排""国庆7天去云南路线""周末广州亲子游预算2000"
适用于需求模糊或复杂的场景:
- 不知道怎么安排行程
- 不知道去哪玩
- 有预算/时间等约束条件
- 需要跨品类整合(酒店+景点+行程)
示例:规划"带孩子去三亚玩5天,预算8000"
数据来源
数据来源于官方旅行商品库,价格实时更新,点击链接可直接预订/购票。
License
MIT
Metadata
Release files for mcp-travel-search 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| mcp_travel_search-0.2.0.tar.gz | 6.8 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mcp_travel_search-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 15.5 kB
Release files / mcp_travel_search-0.2.0.tar.gz
| Download URL | mcp_travel_search-0.2.0.tar.gz |
|---|---|
| Size | 6.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ec5343307b98636eb194a6121a6ccd5a84d4ae889df65dfba6075857ff7a061b
|
|
BLAKE2b-256 checksum How to use checksums |
cc9e08c78ae67b2fe6d36c57a2c568aa36d9dd1ecd6ab80b23ee3de9e75af470
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Release files / mcp_travel_search-0.2.0-py3-none-any.whl
| Download URL | mcp_travel_search-0.2.0-py3-none-any.whl |
|---|---|
| Size | 8.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
efb94c97524eae8e21f3b5dbe062488c8d23bc26accd1e45dc3b2b71b4adfb99
|
|
BLAKE2b-256 checksum How to use checksums |
30d154f578387a6da60a6d643c57c8b33b02877d09e0a92bf9a3b3093c29b41d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Security for mcp-travel-search 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.