MCP Weather Service

MCP Weather Service

A weather service built using Model-Context-Protocol (MCP) that provides current weather and forecasts for Indian cities using WeatherAPI.com.

Category
访问服务器

README

MCP Weather Service

A weather service built using Model-Context-Protocol (MCP) that provides current weather and forecasts for Indian cities using WeatherAPI.com.

Prerequisites

  • Python 3.13 or higher
  • uv package manager
  • WeatherAPI.com API key
  • Groq API key (for the chat interface)
  • Claude for Desktop (for testing with Claude)

Installation

  1. Clone the repository:
git clone <your-repo-url>
cd mcp-server
  1. Create a .env file in the project root with your API keys:
# WeatherAPI.com API Key
WEATHER_API_KEY=your_weather_api_key_here

# Groq API Key
GROQ_API_KEY=your_groq_api_key_here
  1. Install dependencies using uv:
uv pip install -e .

Running the Service

Development Mode

To run the weather service in development mode:

uv run mcp dev server/weather.py

Install and Run

To install and run the service on desktop claude:

uv run mcp install server/weather.py

Setting up weather.json

The weather.json configuration file is required for the chat interface.

1, Testing your server with Claude for Desktop:

  • Open VS Code and run:
    code $env:AppData\Claude\claude_desktop_config.json
    
  • Add the following configuration:
    {
        "mcpServers": {
            "weather": {
                "command": "uv",
                "args": [
                    "--directory",
                    "C:\\ABSOLUTE\\PATH\\TO\\YOUR\\mcp-server",
                    "run",
                    "server/weather.py"
                ]
            }
        }
    }
    
  • Replace C:\\ABSOLUTE\\PATH\\TO\\YOUR\\mcp-server with your actual project path
  1. For Chat Interface (client.py):

    • The weather.json file should be in your server directory
    • Make sure it contains:
      {
          "mcpServers": {
              "weather": {
                  "command": "uv",
                  "args": [
                      "--directory",
                      "C:\\ABSOLUTE\\PATH\\TO\\YOUR\\mcp-server",
                      "run",
                      "server/weather.py"
                  ]
              }
          }
      }
      
    • Replace C:\\ABSOLUTE\\PATH\\TO\\YOUR\\mcp-server with your actual project path
  2. Restart Claude for Desktop after making changes

Using the Chat Interface

Run the chat client to interact with the weather service:

python server/client.py

The chat interface supports:

  • Getting current weather for any Indian city
  • Getting 3-day weather forecasts
  • Natural language queries about weather

Commands:

  • Type 'exit' or 'quit' to end the conversation
  • Type 'clear' to clear conversation history

Features

  • Current weather information:

    • Temperature in Celsius
    • Weather condition
    • Humidity
    • Wind speed
    • Last updated timestamp
  • 3-day weather forecast:

    • Daily high and low temperatures
    • Weather conditions
    • Date-specific forecasts

Project Structure

mcp-server/
├── server/
│   ├── weather.py      # Weather service implementation
│   ├── client.py       # Chat interface
│   └── weather.json    # MCP server configuration
├── .env               # API keys configuration
├── pyproject.toml     # Project dependencies
└── README.md         # This file

API Keys

  1. WeatherAPI.com:

    • Sign up at WeatherAPI.com
    • Get your free API key
    • Add it to .env as WEATHER_API_KEY
  2. Groq API:

    • Sign up at Groq Console
    • Get your API key
    • Add it to .env as GROQ_API_KEY

Contributing

Feel free to submit issues and enhancement requests!

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