Weather MCP Server

Weather MCP Server

Provides weather information including alerts and forecasts for any location, web search capabilities through Brave Search API, and basic math operations. Includes weather-based event suggestions to help users plan activities based on current conditions.

Category
访问服务器

README

Weather MCP Server

A Model Context Protocol (MCP) server that provides weather information, web search capabilities, and basic math operations using FastMCP.

Features

🌤️ Weather Tools

  • get_alerts: Get weather alerts for any US state
  • get_forecast: Get detailed weather forecast for any location (latitude/longitude)

🔍 Search Tools

  • brave_search: Search the web using Brave Search API
  • add_numbers: Add two numbers together

💡 Prompts

  • suggest_events: Get comprehensive weather data and event suggestions for a location

Prerequisites

  • Python 3.11 or higher
  • uv package manager
  • Brave Search API key (free from Brave Search API)

Installation

  1. Clone and navigate to the project:

    cd /opt/projects/mcp-hack/weather
    
  2. Install dependencies:

    uv sync
    

Configuration

The server uses a hardcoded Brave Search API key. If you want to use your own API key, you can:

  1. Get a free API key from Brave Search API
  2. Update the BRAVE_API_KEY constant in weather.py

Running the Server

Method 1: Direct Python execution

uv run python weather.py

Method 2: Using the main module

uv run python main.py

Method 3: Using uv with module execution

uv run -m weather

Usage Examples

Once the server is running, you can use the following tools:

Weather Tools

# Get weather alerts for California
get_alerts("CA")

# Get forecast for San Francisco (37.7749, -122.4194)
get_forecast(37.7749, -122.4194)

Search Tool

# Search the web with default 3 results
brave_search("python programming tutorials")

# Search with custom result count
brave_search("weather forecast San Francisco", 5)

Math Tool

# Add two numbers
add_numbers(15.5, 24.3)

Prompts

# Get weather-based event suggestions
suggest_events("San Francisco")
# or with coordinates
suggest_events("37.7749,-122.4194")

API Integration

This server integrates with:

  • National Weather Service API: For weather data and alerts
  • Brave Search API: For web search functionality
  • FastMCP: For MCP server implementation
  • LangChain Community: For Brave Search tool integration

Development

Project Structure

weather/
├── weather.py          # Main MCP server with all tools
├── main.py            # Alternative entry point
├── pyproject.toml     # Project dependencies
├── uv.lock           # Dependency lock file
└── README.md         # This file

Adding New Tools

To add new tools, follow the FastMCP pattern:

@mcp.tool()
async def your_tool_name(param1: str, param2: int = 10) -> str:
    """Tool description.
    
    Args:
        param1: Description of parameter 1
        param2: Description of parameter 2 (default: 10)
    """
    # Your tool logic here
    return "Tool result"

Troubleshooting

Common Issues

  1. "BRAVE_SEARCH_API_KEY environment variable not set"

    • The API key is hardcoded in the server, but if you see this error, check that BRAVE_API_KEY is properly set in weather.py
  2. Weather API errors

    • Ensure you're using valid US state codes (2 letters) for alerts
    • Verify latitude/longitude coordinates are valid for forecasts
  3. Import errors

    • Run uv sync to ensure all dependencies are installed
    • Make sure you're using Python 3.11 or higher

Dependencies

Key dependencies include:

  • fastmcp: MCP server framework
  • httpx: HTTP client for API requests
  • langchain-community: Brave Search integration
  • langchain-core: Core LangChain functionality

License

This project is part of the MCP hack and is provided as-is for educational and development purposes.

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