MCP Weather
A TypeScript-based Model Context Protocol server that enables Claude Desktop to fetch real-time weather data via external weather APIs. It provides a simple integration for users to query current weather information through natural language interactions.
README
MCP Weather - Claude Desktop Integration
This project is an example MCP (Model Context Protocol) server designed for use with the Claude Desktop application. It is built to work seamlessly with Claude Desktop.
Features
- TypeScript-based MCP server
- Weather query via OpenWeather API
- Easy integration with Claude Desktop
Project Structure
.
├── package.json
├── tsconfig.json
├── src/
│ └── index.ts
├── claude_desktop_config.json
Installation
Requirements
- Node.js (v16 or higher)
- npm
- Claude Desktop (https://desktop.anthropic.com/)
Setup
- Clone the repository:
git clone <repository-url> cd mcp-weather - Install dependencies:
npm install - Create a
.envfile and fill it as follows:WEATHER_API_URL=https://api.weatherapi.com/v1/current.json WEATHER_API_KEY=<your_API_KEY>
Claude Desktop Integration
-
In Claude Desktop, go to
File -> Settings -> Developer -> Edit Config. -
Add a block similar to the example below to the config file (edit the file paths to match your own system):
{ "mcpServers": { "weather": { "command": "npx", "args": ["tsx", "C:/your/path/mcp-weather/src/index.ts"], "cwd": "C:/your/path/mcp-weather" } } }Note: Replace
C:/your/path/with the actual path to your project on your computer. -
Save the settings and restart Claude Desktop.
.env File and Path Setting
In src/index.ts, the path to the .env file is set to the project root by default:
import dotenv from "dotenv";
dotenv.config({
// Path to your .env file. Edit as needed, e.g.: path: "C:/your/path/.env"
path: ".env", // By default, uses the .env file in the project root
});
If your .env file is in a different directory, update the path parameter accordingly.
Usage
To start the project:
npm start
Or to run the main file directly:
npx ts-node src/index.ts
Build
To compile the TypeScript code:
npm run build
Contributing
Contributions are welcome! Please open issues or submit pull requests for improvements or bug fixes.
License
MIT License
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。