mcp-poc
A proof-of-concept MCP server that provides weather information using the Open-Meteo API, with tools for greeting, getting weather by coordinates, and by location name.
README
MCP Weather Server POC
A proof of concept MCP (Model Context Protocol) server that integrates with external REST APIs to provide weather information.
Features
- hello: Simple greeting tool
- get_weather: Get weather by latitude and longitude coordinates
- get_weather_by_location: Get weather by city/location name
Weather Data
This POC uses the Open-Meteo API (free, no API key required):
- Forecast data: https://api.open-meteo.com/v1/forecast
- Geocoding: https://geocoding-api.open-meteo.com/v1/search
Setup
1. Create Virtual Environment (if not already created)
python -m venv venv
2. Activate Virtual Environment
On Windows (PowerShell):
(Set-ExecutionPolicy -Scope Process -ExecutionPolicy RemoteSigned) ; (& .\venv\Scripts\Activate.ps1)
On Windows (CMD):
venv\Scripts\activate
On macOS/Linux:
source venv/bin/activate
3. Install Dependencies
pip install -r requirements.txt
Running the Server
python server.py
The server will start and be ready to receive requests from MCP clients.
Usage Examples
In an MCP Client
Get weather by location name
Tool: get_weather_by_location
Parameters:
- location: "London"
Response:
Current Weather in London, United Kingdom:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Temperature: 15.2°C
Humidity: 72%
Condition: Partly cloudy
Wind Speed: 12.5 km/h
Time: 2024-06-25T14:30
Get weather by coordinates
Tool: get_weather
Parameters:
- latitude: 51.5074
- longitude: -0.1278
Simple greeting
Tool: hello
Parameters:
- name: "World"
Testing with curl (if exposed via HTTP)
curl http://localhost:8000/tools/call \
-X POST \
-H "Content-Type: application/json" \
-d '{"tool": "get_weather_by_location", "params": {"location": "Tokyo"}}'
Supported Weather Codes
The server uses WMO weather codes and interprets them as:
- 0: Clear sky
- 1-3: Various cloud coverage
- 45-48: Fog conditions
- 51-82: Various precipitation types
- 95-99: Thunderstorm conditions
Architecture
┌──────────────────┐
│ MCP Client │
└────────┬─────────┘
│
│ (MCP Protocol)
│
┌────────▼─────────────────┐
│ MCP Server (FastMCP) │
│ ┌──────────────────────┐│
│ │ Tools: ││
│ │ - hello ││
│ │ - get_weather ││
│ │ - get_weather_... ││
│ └──────────────────────┘│
└────────┬─────────────────┘
│
│ (REST API)
│
┌────────▼──────────────────┐
│ Open-Meteo API │
│ - Weather Data │
│ - Geocoding │
└───────────────────────────┘
Error Handling
The server includes error handling for:
- Network timeouts
- Connection errors
- Invalid locations
- HTTP errors
- Malformed responses
License
MIT License
Future Enhancements
- Add historical weather data
- Add weather forecasts (multi-day)
- Add severe weather alerts
- Add precipitation probability
- Support multiple weather providers
- Add caching for repeated requests
- Add UV index information
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。