返回 MCP 目录
public公开dns本地运行

Surf MCP潮汐服务器

使用纬度和经度获取任何位置的潮汐信息,提供详细的潮汐数据,包括高低潮汐和站点信息,并自动处理UTC时区。

article

README

Surf MCP Server

MCP server for people who surf waves and the web.

Diagram

Letter Dot Grid - 5 dpi

Video Demo

https://github.com/user-attachments/assets/0a4453e2-66df-4bf5-8366-8538cda366ed

Features

  • Fetch tide information for any location using latitude and longitude
  • Support for date-specific tide queries
  • Detailed tide data including high/low tides and station information
  • Automatic time zone handling (UTC)

Prerequisites

  • Python 3.x
  • Storm Glass API key

Getting Your Storm Glass API Key

  1. Visit Storm Glass
  2. Click "Try for Free" or "Sign In" to create an account
  3. Once registered, you'll receive your API key

Note on API Usage Limits:

  • Free tier: 10 requests per day
  • Paid plans available:
    • Small: 500 requests/day (€19/month)
    • Medium: 5000 requests/day (€49/month)
    • Large: 25,000 requests/day (€129/month)
    • Enterprise: Custom plans available

Choose a plan based on your usage requirements. The free tier is suitable for testing and personal use.

Installation

  1. Clone the repository:
git clone https://github.com/ravinahp/surf-mcp.git
cd surf-mcp
  1. Install dependencies using uv:
uv sync

Note: We use uv instead of pip since the project uses pyproject.toml for dependency management.

Configure as MCP Server

To add this tool as an MCP server, you'll need to modify your Claude desktop configuration file. This configuration includes your Storm Glass API key, so you won't need to set it up separately.

The configuration file location depends on your operating system:

  • MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json

Add the following configuration to your JSON file:

{
    "surf-mcp": {
        "command": "uv",
        "args": [
            "--directory",
            "/Users/YOUR_USERNAME/Code/surf-mcp",
            "run",
            "surf-mcp"
        ],
        "env": {
            "STORMGLASS_API_KEY": "your_api_key_here"
        }
    }
}

⚠️ IMPORTANT:

  1. Replace YOUR_USERNAME with your actual system username
  2. Replace your_api_key_here with your actual Storm Glass API key
  3. Make sure the directory path matches your local installation

Deployment

Building

To prepare the package:

  1. Sync dependencies and update lockfile:
uv sync
  1. Build package:
uv build

This will create distributions in the dist/ directory.

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector with this command:

npx @modelcontextprotocol/inspector uv --directory /path/to/surf-mcp run surf-mcp

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

The Inspector provides:

  • Real-time request/response monitoring
  • Input/output validation
  • Error tracking
  • Performance metrics

Usage

The service provides a FastMCP tool for getting tide information:

@mcp.tool()
async def get_tides(latitude: float, longitude: float, date: str) -> str:
    """Get tide information for a specific location and date."""

Parameters:

  • latitude: Float value representing the location's latitude
  • longitude: Float value representing the location's longitude
  • date: Date string in YYYY-MM-DD format

Example Response:

Tide Times:
Time: 2024-01-20T00:30:00+00:00 (UTC)
Type: HIGH tide
Height: 1.52m

Time: 2024-01-20T06:45:00+00:00 (UTC)
Type: LOW tide
Height: 0.25m

Station Information:
Name: Sample Station
Distance: 20.5km from requested location

Use Cases

Example #1: Finding the Best Surf Time

You can use this tool to determine the optimal surfing time at your favorite beach & the closest station. Generally, the best surfing conditions are during incoming (rising) tides, about 2 hours before high tide.

Example prompt to Claude:

Screenshot 2025-01-07 at 12 55 47 PM

Note: Different beaches may have different optimal tide conditions based on their specific geography and break type. This tool also provides station distance information which should be considered alongside tide information. (ie. longer station distance means higher change of innacuracy - you can ask Claude for this as well when prompting).

Error Handling

The service includes robust error handling for:

  • API request failures
  • Invalid coordinates
  • Missing or invalid API keys
  • Network timeouts
help

运行方式说明

cloud

托管运行

托管运行通常表示这个 MCP Server 由服务方环境承载,用户一般按页面提供的连接方式或授权流程接入,不需要在本地长期启动一个 MCP 进程

  1. 打开服务方连接页
  2. 完成授权或复制端点
  3. 在 MCP 客户端中连接
terminal

本地运行 / 其它方式

本地运行通常需要用户在自己的电脑或服务器上安装依赖,把 server_config 复制到 MCP 客户端,并按 env_schema 补齐环境变量、密钥或其它配置

  1. 复制 server_config
  2. 安装所需依赖
  3. 补齐环境变量后重启客户端