Surf Forecast MCP
Provides surf forecast data including swell height, period, direction, and wind conditions for any location worldwide using the Open-Meteo Marine API. It also includes tools to find the best day to surf and integrates with MCP clients via a Python server.
README
Surf Forecast MCP
A Python-based MCP that uses the Open-Meteo Marine API (free, no API key required) to forecast swell height, swell period, swell direction, and wind conditions. Search for any city name and the system will automatically convert it to latitude and longitude coordinates to retrieve weather data and wave forecasts. Includes a surf forecast MCP server that provides wave and surf conditions for any location worldwide.
You can use the backend or view the results for better understanding using Streamlit.
Running the MCP Server 🔥

Here is how you activate following the mcp json example
{
"mcpServers": {
"surf-forecast": {
"command": "python",
"args": ["server.py"]
}
}
}

Example of forecasting

Example of bestday

How to start
# 1) criar e ativar venv (opcional)
python -m venv .venv
source .venv/bin/activate # mac/linux
# .venv\Scripts\activate # windows
# 2) instalar deps
pip install -r requirements.txt
# 3) run the Surf Forecast API
uvicorn backend.main:app --reload
# 4) run the frontend (Streamlit)
python -m streamlit run frontend/app.py
Key Makefile targets (use make help to see in terminal)
make help - Show this help message
make setup - Create virtual environment and install dependencies
make install - Install dependencies
make install-dev - Install dependencies + dev tools (black, ruff)
make venv - Create virtual environment
make format - Format code with black
make lint - Lint code with ruff
make check - Format and lint code
make server - Run FastAPI backend (uvicorn)
make mcp - Run MCP server
make frontend - Run Streamlit frontend
make test - Run tests (if available)
make clean - Remove cache and temporary files
make clean-all - Clean everything including virtual environment
make dev - Setup development environment
Error Handling
The service includes robust error handling for:
- API request failures
- Invalid coordinates
- Network timeouts
Response Example: Using Pydantic principles and FastAPI
{
"location": "Monte de Caparica, Almada, Setúbal, 2825-096, Portugal",
"latitude": 38.6637429,
"longitude": -9.198197,
"current_conditions": {
"timestamp": "2026-01-31T00:00",
"wave_height_m": 4.5,
"swell_wave_height_m": 4.42,
"wind_wave_height_m": 0.8,
"wave_direction_deg": 289,
"swell_wave_direction_deg": 289,
"wave_period_s": 12.15,
"swell_wave_period_s": 10.4,
"wind_speed_knots": 9,
"wind_direction_deg": 288,
"wind_gusts_knots": 23.1,
"temperature_c": 12.5
},
"hourly_forecast": [
{
"timestamp": "2026-01-31T03:00",
"wave_height_m": 4.4,
"swell_wave_height_m": 4.36,
"wind_wave_height_m": 0.48,
"wave_direction_deg": 291,
"swell_wave_direction_deg": 291,
"wave_period_s": 12.4,
"swell_wave_period_s": 10.45,
"wind_speed_knots": 5.9,
"wind_direction_deg": 278,
"wind_gusts_knots": 15.9,
"temperature_c": 11.7
},
{
"timestamp": "2026-01-31T06:00",
"wave_height_m": 4.24,
"swell_wave_height_m": 4.22,
"wind_wave_height_m": 0.42,
"wave_direction_deg": 292,
"swell_wave_direction_deg": 292,
"wave_period_s": 12.5,
"swell_wave_period_s": 10.55,
"wind_speed_knots": 4.1,
"wind_direction_deg": 275,
"wind_gusts_knots": 13.6,
"temperature_c": 10.9
},
{
"timestamp": "2026-01-31T09:00",
"wave_height_m": 4.06,
"swell_wave_height_m": 4.04,
"wind_wave_height_m": 0.32,
"wave_direction_deg": 293,
"swell_wave_direction_deg": 293,
"wave_period_s": 12.5,
"swell_wave_period_s": 10.5,
"wind_speed_knots": 4.5,
"wind_direction_deg": 263,
"wind_gusts_knots": 11.3,
"temperature_c": 11.7
},
{
"timestamp": "2026-01-31T12:00",
"wave_height_m": 3.9,
"swell_wave_height_m": 3.88,
"wind_wave_height_m": 0.3,
"wave_direction_deg": 294,
"swell_wave_direction_deg": 294,
"wave_period_s": 12.5,
"swell_wave_period_s": 10.5,
"wind_speed_knots": 7.3,
"wind_direction_deg": 279,
"wind_gusts_knots": 18.9,
"temperature_c": 14.6
}
],
"forecast_5day": [
{
"date": "2026-01-31",
"wave_height_max_m": 4.5,
"swell_wave_height_max_m": 4.42,
"wind_wave_height_max_m": 0.8,
"wave_direction_dominant_deg": 292,
"swell_wave_direction_dominant_deg": 292,
"wave_period_max_s": 12.6,
"swell_wave_period_max_s": 10.6,
"wind_speed_max_knots": 9,
"wind_direction_dominant_deg": 262,
"wind_gusts_max_knots": 23.1,
"temperature_max_c": 15.2,
"temperature_min_c": 10.9
},
{
"date": "2026-02-01",
"wave_height_max_m": 3.16,
"swell_wave_height_max_m": 3.12,
"wind_wave_height_max_m": 1.28,
"wave_direction_dominant_deg": 283,
"swell_wave_direction_dominant_deg": 289,
"wave_period_max_s": 12.35,
"swell_wave_period_max_s": 11.2,
"wind_speed_max_knots": 12.5,
"wind_direction_dominant_deg": 223,
"wind_gusts_max_knots": 30.7,
"temperature_max_c": 15.1,
"temperature_min_c": 13.3
},
{
"date": "2026-02-02",
"wave_height_max_m": 3.8,
"swell_wave_height_max_m": 3.78,
"wind_wave_height_max_m": 2.3,
"wave_direction_dominant_deg": 274,
"swell_wave_direction_dominant_deg": 284,
"wave_period_max_s": 11.15,
"swell_wave_period_max_s": 11.85,
"wind_speed_max_knots": 16.1,
"wind_direction_dominant_deg": 254,
"wind_gusts_max_knots": 48,
"temperature_max_c": 13.9,
"temperature_min_c": 9.8
},
{
"date": "2026-02-03",
"wave_height_max_m": 4.82,
"swell_wave_height_max_m": 4.26,
"wind_wave_height_max_m": 2.32,
"wave_direction_dominant_deg": 279,
"swell_wave_direction_dominant_deg": 283,
"wave_period_max_s": 12.1,
"swell_wave_period_max_s": 10.95,
"wind_speed_max_knots": 12,
"wind_direction_dominant_deg": 247,
"wind_gusts_max_knots": 32.5,
"temperature_max_c": 14,
"temperature_min_c": 9.4
},
{
"date": "2026-02-04",
"wave_height_max_m": 4.98,
"swell_wave_height_max_m": 4.48,
"wind_wave_height_max_m": 2.4,
"wave_direction_dominant_deg": 270,
"swell_wave_direction_dominant_deg": 281,
"wave_period_max_s": 11.05,
"swell_wave_period_max_s": 10.6,
"wind_speed_max_knots": 15.9,
"wind_direction_dominant_deg": 248,
"wind_gusts_max_knots": 38.7,
"temperature_max_c": 15.4,
"temperature_min_c": 14.8
}
],
"surf_quality_notes": "big waves - advanced surfers only | light breeze - good conditions | long period swell - clean waves expected | swell dominant - cleaner conditions"
}
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。