travel-mcp-server

travel-mcp-server

Enables complex travel planning by integrating flight and hotel search via Booking.com API and Google Maps for location context.

Category
访问服务器

README

✈️ Multi Context Protocol (MCP) Server

🌟 Overview

This is a generalized travel mcp server that allows you to ask complex travel planning questions. Try the following

  • I need to be at the Google office tomorrow by 4pm. What is the latest flight I need to take?
  • I would like to stay at a reasonably priced hotel 15 minutes walk from the Eiffel tower, recommend some options.

🔧 Supported Functions

🛫 search-flights

Searches for available flights between two airports via Booking.com's API.

📅 today

Provides the current date to the LLM, ensuring it has up-to-date temporal context.

🏨 search-hotels

Search for available hotels and accommodations.

🔮 Features to Come

🚗 search-car-rentals

Find car rental options at your destination.

hotel-reviews

Access reviews for hotels and accommodations.

🚕 search-taxis

Find taxi and transfer services at your destination.

📦 Installation

This MCP server can be used with either Claude Desktop or your own client.

Pre-requisites

  1. Go to RapidAPI, and look for the booking.com API. Issue yourself a key
  2. Go to google cloud and issue yourself a Google Maps API key.

Use with Claude Desktop

In order to work with Claude Desktop, use the below claude_desktop_config.json

{
  "mcpServers": {
    "travel": {
      "command": "npx",
      "args": ["travel-mcp-server"],
      "env": {
        "BOOKING_COM_API_KEY": "<YOUR_BOOKING_DOT_COM_API_KEY>"
      }
    },
    "google-maps": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GOOGLE_MAPS_API_KEY",
        "mcp/google-maps"
      ],
      "env": {
        "GOOGLE_MAPS_API_KEY": "<YOUR_GOOGLE_MAPS_API_KEY>"
      }
    }
  }
}

You will need to go get a google maps API key in order to use this.

Programmatic Use

If you want to use this programmatically, here is a code snippet.

class TravelClient {
  private flightsClient: Client;
  private mapsClient: Client;
  private toolDefinitions: any[] = [];

  constructor() {
    this.flightsClient = new Client(
      { name: "FlightsApp", version: "1.0.0" },
      { capabilities: { tools: {}, resources: {}, prompts: {} } }
    );
    this.mapsClient = new Client(
      { name: "MapsApp", version: "1.0.0" },
      { capabilities: { tools: {}, resources: {}, prompts: {} } }
    );
  }

  async initialize() {
    console.log("Initializing MCP clients...");
    try {
      const flightsTransport = new StdioClientTransport({
        command: "node",
        args: ["../../node_modules/travel-mcp-server/build/index.js"],
      });

      console.log("GOOGLE MAPS API KEY", process.env.GOOGLE_MAPS_API_KEY);
      const mapsTransport = new StdioClientTransport({
        command: process.execPath,
        args: [
          "../../node_modules/@modelcontextprotocol/server-google-maps/dist/index.js",
        ],
        env: {
          GOOGLE_MAPS_API_KEY: process.env.GOOGLE_MAPS_API_KEY || "",
        },
      });

      await Promise.all([
        this.flightsClient.connect(flightsTransport),
        this.mapsClient.connect(mapsTransport),
      ]);

      // Discover tools from both servers
      console.log("Discovering tools...");
      const [flightsTools, mapsTools] = await Promise.all([
        this.flightsClient.listTools(),
        this.mapsClient.listTools(),
      ]);

      // Combine tools from both servers
      this.toolDefinitions = [
        ...flightsTools.tools.map((tool) => ({
          name: tool.name,
          description: tool.description || `Tool: ${tool.name}`,
          input_schema: tool.inputSchema,
        })),
        ...mapsTools.tools.map((tool) => ({
          name: tool.name,
          description: tool.description || `Tool: ${tool.name}`,
          input_schema: tool.inputSchema,
        })),
      ];

      console.log(`Discovered ${this.toolDefinitions.length} tools`);
      return this;
    } catch (error) {
      console.error("Error initializing MCP clients:", error);
      throw error;
    }
  }

  async callTool(toolName: string, parameters: any) {
    const tool = this.toolDefinitions.find((t) => t.name === toolName);
    if (!tool) {
      throw new Error(`Tool ${toolName} not found`);
    }

    // Determine which client to use based on the tool name
    const client = toolName.includes("maps")
      ? this.mapsClient
      : this.flightsClient;

    const toolRequest = {
      name: toolName,
      arguments: parameters,
    };

    const result = await client.callTool(toolRequest);
    return result;
  }

  async getToolDefinitions() {
    return this.toolDefinitions;
  }
}

export default TravelClient;

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
Kagi MCP Server

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。

官方
精选
Python
graphlit-mcp-server

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。

官方
精选
TypeScript
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选