GIS MCP Server

Instructions

Implementation Reference

• src/gis_mcp/rasterio_functions.py:1008-1045 (handler)

  The core handler function for the 'raster_histogram' MCP tool. It reads the input raster, computes histograms for each band using numpy.histogram, and returns the results per band including bin edges.

  @gis_mcp.tool()
  def raster_histogram(
      source: str,
      bins: int = 256
  ) -> Dict[str, Any]:
      """
      Compute histogram of pixel values for each band.
  
      Parameters:
      - source: path to input raster.
      - bins:   number of histogram bins.
      """
      try:
          import rasterio
          import numpy as np
          import os
  
          src_path = os.path.expanduser(source.replace("`", ""))
          histograms = {}
  
          with rasterio.open(src_path) as src:
              for i in range(1, src.count + 1):
                  band = src.read(i, masked=True)
                  hist, bin_edges = np.histogram(band.compressed(), bins=bins)
                  histograms[f"Band {i}"] = {
                      "histogram": hist.tolist(),
                      "bin_edges": bin_edges.tolist()
                  }
  
          return {
              "status": "success",
              "histograms": histograms,
              "message": f"Histogram computed for all bands."
          }
  
      except Exception as e:
          raise ValueError(f"Failed to compute histogram: {e}")

• src/gis_mcp/rasterio_functions.py:11-35 (registration)

  MCP resource that lists all available rasterio operations, including 'raster_histogram', serving as a tool discovery/registration point.

  @gis_mcp.resource("gis://operation/rasterio")
  def get_rasterio_operations() -> Dict[str, List[str]]:
      """List available rasterio operations."""
      return {
          "operations": [
              "metadata_raster",
              "get_raster_crs",
              "clip_raster_with_shapefile",
              "resample_raster",
              "reproject_raster",
              "weighted_band_sum",
              "concat_bands",
              "raster_algebra",
              "compute_ndvi",
              "raster_histogram",
              "tile_raster",
              "raster_band_statistics",
              "extract_band",
              "zonal_statistics",
              "reclassify_raster",
              "focal_statistics",
              "hillshade",
              "write_raster"
          ]
      }