Weather Agent MCP Server

Weather Agent MCP Server

Enables users to get current weather information for any city using the OpenWeatherMap API. Returns formatted weather data including temperature, humidity, and weather description through natural language queries.

Category
访问服务器

README

Weather Agent MCP Server

A sample MCP server that provides weather information for a specified city using the OpenWeatherMap API.

Description

This project implements a simple Model Context Protocol (MCP) server called "Weather Bot". It exposes a single tool that fetches current weather data for a given city, including temperature in Celsius, humidity, and weather description. The server communicates via standard I/O (stdio) and can be integrated with MCP-compatible clients.

Tested on Apple M1 Air.

<img src="Claude-Desktop.png" alt="Test Result" width="500px"/>

Features

  • Get current weather information for any city
  • Returns formatted weather data including description, temperature (°C), and humidity
  • Integrates with OpenWeatherMap API for up-to-the-minute weather data

Installation

  1. Clone or download this repository to your local machine.

  2. Install the required dependencies:

    pip install -r requirements.txt
    

Configuration

  1. Get an API key from OpenWeatherMap

  2. Create a .env file in the project root and add your API key:

    WEATHER_API_KEY=your_api_key_here
    

    Security Note: Never commit your .env file to version control. Ensure it's included in your .gitignore.

Usage

Run the MCP server using:

python weather_agent.py

The server starts and listens for MCP protocol messages via stdio. It can be integrated with MCP-compatible applications or clients.

Integration with Claude Desktop

To test this MCP server with Claude Desktop, follow these steps:

  1. Ensure Claude Desktop is installed on your machine.

  2. Locate your claude_desktop_config.json file. On macOS, it's typically located at ~/Library/Application Support/Claude/claude_desktop_config.json. You can also open the path by openging via UI, Claude > Settings > Developer > Edit Config.

  3. Open the claude_desktop_config.json file and add the following configuration inside the JSON object (add to the "mcpServers" object if it exists, or create it):

{
  "mcpServers": {
    "weather-agent": {
      "command": "python",
      "args": ["/path/to/your/mcp-server/weather_agent.py"]
    }
  }
}

Replace /path/to/your/mcp-server/weather_agent.py with the absolute path to your weather_agent.py file. For example, the path might be /Users/yourusername/Desktop/mcp-server/weather_agent.py.

  1. Save the claude_desktop_config.json file.

  2. Restart Claude Desktop to load the new configuration.

  3. In Claude Desktop, you can now interact with the weather agent. For example, ask Claude: "What's the weather in Tokyo?" and it should use the MCP server to fetch and return the weather information.

Note: Ensure that your API key is configured in the .env file as described in the Configuration section, and that the Python environment is set up to run the script (e.g., the required packages are installed).

API

get_weather(city: str) -> str

Fetches current weather information for the specified city.

Parameters:

  • city: String - The name of the city to get weather for

Returns: A formatted string containing:

  • City name
  • Weather description
  • Current temperature in Celsius
  • Humidity percentage

Example Response:

The current weather in London is overcast clouds with a temperature of 15°C and humidity of 72%.

Dependencies

  • requests: For making HTTP requests to the weather API
  • python-dotenv: For loading environment variables from .env file
  • fastmcp: MCP server framework

Error Handling

If the weather API returns an error or the city is not found, the tool will return an error message indicating the failure to fetch data.

License

This is a sample project. Feel free to modify and use as needed.

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