Surf MCP Server

Instructions

Args:
    latitude: Float value representing the location's latitude
    longitude: Float value representing the location's longitude
    date: Date string in YYYY-MM-DD format
    
Returns:
    Formatted string containing tide information and station details

Implementation Reference

• src/surf/tools.py:12-24 (handler)

  The handler function for the 'get_tides' tool. It is registered via the @mcp.tool() decorator and executes the tool logic by delegating to StormGlassAPI.

  @mcp.tool()
  async def get_tides(latitude: float, longitude: float, date: str) -> str:
      """Get tide information for a specific location and date.
      
      Args:
          latitude: Float value representing the location's latitude
          longitude: Float value representing the location's longitude
          date: Date string in YYYY-MM-DD format
          
      Returns:
          Formatted string containing tide information and station details
      """
      return await api.get_tide_data(latitude, longitude, date) 

• src/surf/stormglass_api.py:63-80 (helper)

  Supporting utility in StormGlassAPI class that performs the actual API request to retrieve tide data, formats parameters, handles the HTTP call, and returns formatted tide information.

  async def get_tide_data(self, latitude: float, longitude: float, date: str) -> str:
      """Get tide information for a specific location and date."""
      url = f"{self.api_base}/tide/extremes/point"
      params = {
          "lat": latitude,
          "lng": longitude,
          "start": f"{date}T00:00:00Z",
          "end": f"{date}T23:59:59Z"
      }
      
      param_string = "&".join(f"{k}={v}" for k, v in params.items())
      full_url = f"{url}?{param_string}"
      
      data = await self.make_request(full_url)
      if not data:
          return "Unable to fetch tide data for this location."
      
      return self.format_tide_data(data) 

• src/surf/server.py:11-11 (registration)

  Execution of the MCP server, making the registered 'get_tides' tool available via stdio transport.

  mcp.run(transport='stdio')