MCP Weather Server

MCP Weather Server

Enables users to get current weather information for any city worldwide using the Open-Meteo API. Provides temperature and wind speed data through natural language queries.

Category
访问服务器

README

MCP Weather Server

A Model Context Protocol (MCP) server that provides weather information for any city using the Open-Meteo API.

Overview

This MCP server implements a simple weather tool that allows you to get current weather conditions for any city worldwide. It uses the Open-Meteo geocoding API to resolve city names to coordinates and then fetches current weather data including temperature and wind speed.

Features

  • City Weather Lookup: Get current weather for any city by name
  • Geocoding Integration: Automatically resolves city names to coordinates
  • Current Conditions: Returns temperature and wind speed information
  • Error Handling: Graceful handling of invalid cities or API failures
  • MCP Compatible: Built using the official MCP SDK

Prerequisites

  • Node.js (version 14 or higher)
  • npm or yarn package manager

Installation

  1. Clone this repository:
git clone <repository-url>
cd mcp-weather-server
  1. Install dependencies:
npm install

Usage

Local Development

Building and Running the Server

  1. Build the TypeScript code:
npm run build
  1. Start the MCP Weather Server:
npm start

Or for development (builds and runs in one command):

npm run dev

The server will start and listen for MCP connections via stdio transport.

Docker Deployment

Quick Start with Docker

  1. Build the Docker images:
./scripts/docker-build.sh
  1. Run in production mode:
./scripts/docker-run.sh production
  1. Run in development mode (with hot reload):
./scripts/docker-run.sh development

Manual Docker Commands

Build production image:

docker build -t mcp-weather-server:latest .

Build development image:

docker build -f Dockerfile.dev -t mcp-weather-server:dev .

Run with Docker Compose (production):

docker-compose up mcp-weather-server

Run with Docker Compose (development):

docker-compose --profile dev up mcp-weather-server-dev

Run standalone container:

docker run -it --rm --name mcp-weather-server mcp-weather-server:latest

Docker Features

  • Multi-stage builds for optimized production images
  • Non-root user for enhanced security
  • Health checks for container monitoring
  • Resource limits for controlled resource usage
  • Development mode with hot reload and volume mounting
  • Node.js Inspector for debugging support
  • Persistent logging with volume mounts

Debugging

MCP Inspector (Recommended)

The MCP Inspector provides a specialized debugging interface for MCP protocol communications:

Start MCP Inspector:

npm run inspector

Start with build and inspector:

npm run dev:inspector

Access the Inspector:

  • Open your browser to http://localhost:5173
  • The inspector provides a web-based interface to:
    • Monitor MCP protocol messages
    • Inspect tool calls and responses
    • Debug server-client communication
    • View real-time message flow

Node.js Debugging

Start with Node.js inspector enabled:

npm run dev:debug

Start with inspector and break on first line:

npm run dev:debug-brk

Watch mode for TypeScript compilation:

npm run dev:watch

Docker Debugging

Run development container with all debugging tools:

./scripts/docker-run.sh development

Or manually:

docker-compose --profile dev up mcp-weather-server-dev

This exposes:

  • Port 9229: Node.js inspector
  • Port 5173: MCP inspector web interface
  • Port 3000: Application port (if needed)

Connecting Debuggers

  1. MCP Inspector (Web Interface):

    • Navigate to http://localhost:5173
    • Configure your MCP server connection
    • Monitor protocol messages in real-time
  2. Chrome DevTools:

    • Open Chrome and navigate to chrome://inspect
    • Click "Configure" and add localhost:9229
    • Your Node.js process should appear under "Remote Target"
    • Click "inspect" to open DevTools
  3. VS Code:

    • Add this configuration to your .vscode/launch.json:
    {
      "type": "node",
      "request": "attach",
      "name": "Attach to MCP Server",
      "address": "localhost",
      "port": 9229,
      "localRoot": "${workspaceFolder}",
      "remoteRoot": "/app",
      "skipFiles": ["<node_internals>/**"]
    }
    
  4. WebStorm/IntelliJ:

    • Create a new "Attach to Node.js/Chrome" configuration
    • Set host to localhost and port to 9229

Debug Scripts Explained

  • inspector: Starts the MCP Inspector web interface
  • dev:inspector: Builds and starts the MCP Inspector
  • dev:debug: Starts with Node.js inspector on port 9229
  • dev:debug-brk: Starts with Node.js inspector and breaks on the first line
  • dev:watch: Runs TypeScript in watch mode for continuous compilation

Debugging Workflow

  1. For MCP Protocol Issues:

    • Use npm run dev:inspector to monitor MCP messages
    • Check tool calls, responses, and protocol compliance
  2. For Code-Level Debugging:

    • Use npm run dev:debug with Chrome DevTools or VS Code
    • Set breakpoints in your TypeScript source files
  3. For Docker Development:

    • Use ./scripts/docker-run.sh development
    • Access both MCP Inspector (port 5173) and Node.js inspector (port 9229)

Available Tools

get-weather

Retrieves current weather information for a specified city.

Parameters:

  • city (string): The name of the city to get weather for

Example Response:

The current temperature in London is 15°C with a wind speed of 12 km/h.

Integration with MCP Clients

This server can be integrated with any MCP-compatible client. The server exposes the get-weather tool that can be called with a city name parameter.

API Dependencies

This server relies on the following free APIs:

  • Open-Meteo Geocoding API: For converting city names to coordinates
  • Open-Meteo Weather API: For fetching current weather data

No API keys are required as Open-Meteo provides free access to their weather data.

Project Structure

mcp-weather-server/
├── src/                    # Source code
│   ├── index.ts           # Main entry point
│   ├── server/            # Server implementation
│   │   └── index.ts       # MCP server setup
│   ├── tools/             # Tool implementations
│   │   └── weather-tool.ts # Weather tool logic
│   ├── types/             # TypeScript type definitions
│   │   └── weather.ts     # Weather-related types
│   └── utils/             # Utility functions
│       └── api.ts         # API client utilities
├── dist/                  # Compiled JavaScript output
├── examples/              # Example configurations
│   └── mcp-config.json   # MCP client configuration example
├── docs/                  # Documentation
├── tests/                 # Test files
├── tsconfig.json         # TypeScript configuration
├── package.json          # Project dependencies and metadata
├── package-lock.json     # Locked dependency versions
├── .gitignore           # Git ignore rules
└── README.md            # This file

Dependencies

  • @modelcontextprotocol/sdk: Official MCP SDK for building servers
  • zod: Schema validation library for input validation

Error Handling

The server includes robust error handling for common scenarios:

  • Invalid City Names: Returns a helpful message when a city cannot be found
  • API Failures: Gracefully handles network errors or API unavailability
  • Malformed Requests: Input validation ensures proper request format

Development

Building

This project uses ES modules. Make sure your Node.js version supports ES modules or use a transpiler if needed.

Testing

Currently, no automated tests are included. To test the server:

  1. Start the server
  2. Connect with an MCP client
  3. Call the get-weather tool with various city names

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Test thoroughly
  5. Submit a pull request

License

ISC License

Changelog

Version 1.0.0

  • Initial release
  • Basic weather lookup functionality
  • MCP SDK integration
  • Open-Meteo API integration

Support

For issues or questions, please open an issue in the repository.

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
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
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
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