JMA Data MCP

Instructions

Implementation Reference

• jma_data_mcp/server.py:58-80 (handler)

  MCP tool handler for search_nearby_stations that wraps the helper function and formats the response.

  @mcp.tool()
  async def search_nearby_stations(
      lat: float,
      lon: float,
      radius_km: float = 50.0,
  ) -> dict:
      """Search AMeDAS stations within a radius from given coordinates.
  
      Args:
          lat: Latitude in decimal degrees
          lon: Longitude in decimal degrees
          radius_km: Search radius in kilometers (default: 50)
  
      Returns:
          List of nearby stations sorted by distance
      """
      stations = search_stations_by_location(lat, lon, radius_km)
      return {
          "count": len(stations),
          "search_center": {"lat": lat, "lon": lon},
          "radius_km": radius_km,
          "stations": stations,
      }

• jma_data_mcp/stations.py:43-79 (helper)

  Core implementation using Haversine formula to compute distances and find nearby stations.

  def search_stations_by_location(
      lat: float,
      lon: float,
      radius_km: float = 50.0
  ) -> list[dict]:
      """Search stations within radius from given location."""
      import math
  
      stations = load_stations()
      results = []
  
      for station in stations.values():
          station_lat = station["location"]["lat"]
          station_lon = station["location"]["lon"]
  
          # Haversine formula for distance calculation
          lat1, lon1 = math.radians(lat), math.radians(lon)
          lat2, lon2 = math.radians(station_lat), math.radians(station_lon)
  
          dlat = lat2 - lat1
          dlon = lon2 - lon1
  
          a = math.sin(dlat/2)**2 + math.cos(lat1) * math.cos(lat2) * math.sin(dlon/2)**2
          c = 2 * math.asin(math.sqrt(a))
  
          # Earth radius in km
          r = 6371
          distance = r * c
  
          if distance <= radius_km:
              result = station.copy()
              result["distance_km"] = round(distance, 2)
              results.append(result)
  
      # Sort by distance
      results.sort(key=lambda x: x["distance_km"])
      return results