GIS MCP Server

Instructions

Implementation Reference

• src/gis_mcp/pysal_functions.py:189-225 (handler)

  The primary handler function for the 'gamma_statistic' tool. It is decorated with @gis_mcp.tool(), loads geospatial data, computes the Gamma spatial autocorrelation statistic using esda.Gamma, handles various attribute names for results, and returns a structured response with status, message, gamma value, p-value, and data preview.

  @gis_mcp.tool()
  def gamma_statistic(shapefile_path: str, dependent_var: str = "LAND_USE", target_crs: str = "EPSG:4326", distance_threshold: float = 100000) -> Dict[str, Any]:
      """Compute Gamma Statistic for spatial autocorrelation."""
      gdf, y, w, (threshold, unit), err = pysal_load_data(shapefile_path, dependent_var, target_crs, distance_threshold)
      if err:
          return {"status": "error", "message": err}
  
      import esda
      stat = esda.Gamma(y, w)
      preview = gdf[['geometry', dependent_var]].head(5).assign(
          geometry=lambda df: df.geometry.apply(lambda g: g.wkt)
      ).to_dict(orient="records")
  
      # Gamma statistic - check for available attributes
      gamma_val = None
      if hasattr(stat, "G"):
          gamma_val = float(stat.G)
      elif hasattr(stat, "gamma"):
          gamma_val = float(stat.gamma)
      elif hasattr(stat, "gamma_index"):
          gamma_val = float(stat.gamma_index)
      
      p_val = None
      if hasattr(stat, "p_value"):
          p_val = float(stat.p_value)
      elif hasattr(stat, "p_sim"):
          p_val = float(stat.p_sim)
      
      return {
          "status": "success",
          "message": f"Gamma Statistic completed successfully (threshold: {threshold} {unit})",
          "result": {
              "Gamma": gamma_val,
              "p_value": p_val,
              "data_preview": preview
          }
      }

• src/gis_mcp/pysal_functions.py:108-135 (helper)

  Supporting helper function 'pysal_load_data' used by gamma_statistic and other PySAL tools. Loads GeoDataFrame, reprojects, creates row-standardized distance-based spatial weights, handles islands, and returns data, values, weights, and threshold info.

  def pysal_load_data(shapefile_path: str, dependent_var: str, target_crs: str, distance_threshold: float):
      """Common loader and weight creation for esda statistics."""
      if not os.path.exists(shapefile_path):
          return None, None, None, None, f"Shapefile not found: {shapefile_path}"
  
      gdf = gpd.read_file(shapefile_path)
      if dependent_var not in gdf.columns:
          return None, None, None, None, f"Dependent variable '{dependent_var}' not found in shapefile columns"
  
      gdf = gdf.to_crs(target_crs)
  
      effective_threshold = distance_threshold
      unit = "meters"
      if target_crs.upper() == "EPSG:4326":
          effective_threshold = distance_threshold / 111000
          unit = "degrees"
  
      y = gdf[dependent_var].values.astype(np.float64)
      import libpysal
      w = libpysal.weights.DistanceBand.from_dataframe(gdf, threshold=effective_threshold, binary=False)
      w.transform = 'r'
  
      for island in w.islands:
          w.weights[island] = [0] * len(w.weights[island])
          w.cardinalities[island] = 0
  
      return gdf, y, w, (effective_threshold, unit), None

• src/gis_mcp/pysal_functions.py:13-28 (registration)

  Resource function listing available ESDA operations including 'gamma_statistic', serving as a discovery/registration point for the tool.

  @gis_mcp.resource("gis://operations/esda")
  def get_spatial_operations() -> Dict[str, List[str]]:
      """List available spatial analysis operations. This is for esda library. They are using pysal library."""
      return {
          "operations": [
              "getis_ord_g",
              "morans_i",
              "gearys_c",
              "gamma_statistic",
              "moran_local",
              "getis_ord_g_local",
              "join_counts",
              "join_counts_local",
              "adbscan"
          ]
      }

• src/gis_mcp/main.py:66-72 (registration)

  Import of pysal_functions module in main.py, which triggers the registration of all @gis_mcp.tool() decorated functions including gamma_statistic via FastMCP decorators.

  from . import (
      geopandas_functions,
      shapely_functions,
      rasterio_functions,
      pyproj_functions,
      pysal_functions,
  )