geo-raster

Level CLocal

Pillar B (expansion) MCP server: windowed Cloud-Optimized GeoTIFF reads, band math (NDVI/NDWI/NBR), zonal statistics, and zonal band math (per-pixel index across separate single-band COGs) over rasters via S3/HTTP byte-range reads (pure-Python COG reader; optional numpy accelerator for zonal statistics via the 'fast' extra).

⭐ 23Development ToolsPythonRepo ↗Updated 2026-09-24

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "aws-samples-sample-geospatial-kiro-power-pack-packages-geo-raster": {
      "command": "uvx",
      "args": [
        "--from",
        "geo-raster",
        "geo-raster"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/aws-samples/sample-geospatial-kiro-power-pack/tree/main/packages/geo-raster

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "aws-samples-sample-geospatial-kiro-power-pack-packages-geo-raster": {
      "command": "uvx",
      "args": [
        "--from",
        "geo-raster",
        "geo-raster"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers