China Travel MCP

China Travel MCP

Provides AI assistants with comprehensive China inbound travel capabilities, including hotel and flight search, attraction discovery, itinerary planning, and travel tips.

Category
Visit Server

README

<!-- mcp-name: io.github.mako202605/china-travel-mcp -->

China Travel MCP

PyPI version License: MIT

An MCP (Model Context Protocol) server that provides AI assistants with comprehensive China inbound travel capabilities. Powered by TripGenie API with Trip.com affiliate booking links.

Features

  • 🏨 Search Hotels — Find hotels across China with real-time pricing and Trip.com booking links
  • ✈️ Search Flights — Query domestic and international flights to/from China
  • 🎫 Search Attractions — Discover top attractions, ticket prices, and opening hours
  • 📋 Plan Itinerary — Generate complete multi-day travel itineraries
  • 💡 Travel Tips — Get practical advice on visa, transportation, payment, safety, and culture

Quick Start

Installation

pip install china-travel-mcp

Run as Standalone Server

china-travel-mcp

Configure in Claude Desktop / Cursor

Add to your MCP client configuration:

{
  "mcpServers": {
    "china-travel": {
      "command": "uvx",
      "args": ["china-travel-mcp"]
    }
  }
}

Build from Source

git clone https://github.com/mako2026/china-travel-mcp.git
cd china-travel-mcp
pip install -e .

Tools

search_hotels

Search hotels in any Chinese city with pricing and booking links.

Parameters:

  • city (required) — City name, e.g. "Beijing", "Shanghai", "Xi'an"
  • check_in — Check-in date (YYYY-MM-DD)
  • check_out — Check-out date (YYYY-MM-DD)
  • guests — Number of guests (default: 2)
  • budget — Budget level, e.g. "budget", "mid-range", "luxury"
  • preferences — Preferences, e.g. "near city center", "with breakfast"

search_flights

Search flights to, from, or within China.

Parameters:

  • origin (required) — Departure city, e.g. "Tokyo", "New York"
  • destination (required) — Arrival city, e.g. "Shanghai", "Beijing"
  • date (required) — Travel date (YYYY-MM-DD)
  • trip_type — "one way" or "round trip" (default: "one way")
  • cabin — "economy", "business", or "first" (default: "economy")

search_attractions

Discover top attractions and things to do in Chinese cities.

Parameters:

  • city (required) — City name, e.g. "Beijing", "Guilin", "Hangzhou"
  • days — Number of sightseeing days (default: 1)
  • interests — Interests, e.g. "history", "nature", "food", "photography"

plan_itinerary

Generate a complete multi-day travel itinerary.

Parameters:

  • city (required) — City name
  • days (required) — Number of days
  • travelers — Number of travelers (default: 2)
  • interests — Travel interests
  • budget — Budget level

get_travel_tips

Get practical travel advice for China.

Parameters:

  • question (required) — Your travel question in natural language

Examples

Ask your AI assistant:

  • "Find me a hotel in Shanghai near the Bund for 3 nights"
  • "What flights are available from Tokyo to Beijing next Friday?"
  • "What are the must-visit attractions in Xi'an?"
  • "Plan a 5-day trip to Chengdu for a couple interested in food and pandas"
  • "Do I need a visa to visit China? What about the 144-hour transit visa?"

Supported Languages

The server defaults to English responses. The underlying API also supports: Chinese (zh), Japanese (ja), Korean (ko), Russian (ru), Spanish (es), French (fr), German (de), Arabic (ar), Thai (th), Vietnamese (vi).

Data Source

Powered by Trip.com — the world's leading online travel platform. All booking links include affiliate tracking.

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured