Travel Planner MCP Server
Minimal TypeScript MCP server providing real flight and hotel search via SerpApi for a personal travel-planning agent.
README
Travel Planner MCP Server
Minimal TypeScript MCP server for a personal travel-planning agent.
Agent-visible tools:
search_flights— real flight options from Google Flights (via SerpApi)search_hotels— real hotel/rental options from Google Hotels (via SerpApi)
Web search is intentionally excluded so it can be handled by your LLM provider's built-in web/search tool. The intended flow:
User
-> LLM travel agent
-> built-in web search for destination facts
-> travel-planner.search_flights for real flight options
-> travel-planner.search_hotels for real hotel options
-> LLM compares tradeoffs and produces the recommendation
Design
Adapter (src/providers) = talks to SerpApi
Normalizer (src/normalizers) = translates SerpApi response into our product shape
LLM = reasons over our product shape
A single SerpApi key powers both engines. The server is a thin wrapper: no booking, payments, itineraries, ranking, or post-booking support — the LLM composes the plan from the structured results.
Install
npm install
Run in mock mode (no API key needed)
npm run mock # TRAVEL_MCP_MOCK=1, returns realistic mock data
Develop / build (live)
cp .env.example .env # set SERPAPI_API_KEY
npm run dev # tsx, live
npm run build && npm start
Test
npm test # input validation, normalizers, provider errors, tool shapes
MCP client config example
{
"mcpServers": {
"travel-planner": {
"command": "node",
"args": ["/absolute/path/to/travel-planner-mcp/build/index.js"],
"env": {
"SERPAPI_API_KEY": "your_serpapi_key",
"DEFAULT_CURRENCY": "BRL",
"DEFAULT_MARKET": "BR",
"DEFAULT_LOCALE": "pt-BR"
}
}
}
}
Set TRAVEL_MCP_MOCK=1 in env to run the client against mock data.
Environment variables
| Variable | Required | Notes |
|---|---|---|
SERPAPI_API_KEY |
live mode | SerpApi key for both engines |
SERPAPI_BASE_URL |
no | defaults to https://serpapi.com/search.json |
DEFAULT_CURRENCY |
no | e.g. BRL, USD |
DEFAULT_MARKET |
no | Google gl country code, e.g. BR |
DEFAULT_LOCALE |
no | Google hl language code, e.g. pt-BR |
REQUEST_TIMEOUT_MS |
no | supplier call timeout, default 15000 |
TRAVEL_MCP_MOCK |
no | 1 to use mock data instead of SerpApi |
Notes
Supplier-specific request building is isolated in src/providers/*
(serpapi.ts is the shared client), and SerpApi → product-shape mapping lives in
src/normalizers/*. Flight/hotel result shapes are FlightOption / HotelOption.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。