gdal-mcp

Overview

GDAL MCP is a comprehensive Model Context Protocol server that enables AI agents to perform sophisticated geospatial analysis using Python libraries like Rasterio, GeoPandas, and PyProj. Its unique reflection middleware system requires AI to justify methodological decisions before execution, creating a conversation about the 'why' rather than just executing the 'what'. This approach prevents silent failures in geospatial operations, documents methodology for reproducibility, and maintains a 75% cache hit rate by reusing justifications across operations. The server provides 13 production-ready tools for both raster and vector data operations with comprehensive documentation.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• raster_info

  Inspect metadata of raster files (CRS, resolution, bands, nodata)

  Try:What's the CRS of this raster?Try:Show me the metadata for this DEM file
• raster_convert

  Convert raster formats with compression and overviews

  Try:Convert this GeoTIFF to COG formatTry:Convert this raster to PNG with compression
• raster_reproject

  Transform raster to different CRS with reflection

  Try:Reproject this raster to Web MercatorTry:Change the projection of this elevation data
• raster_stats

  Calculate statistics and generate histograms for raster data

  Try:What are the statistics for this raster?Try:Generate a histogram for this image
• raster_query

  Perform spatial window queries on raster data

  Try:Extract values from this raster at these coordinatesTry:Get the pixel values within this bounding box
• vector_info

  Inspect metadata of vector files (CRS, geometry, attributes)

  Try:What's the CRS of this shapefile?Try:Show me the schema of this vector layer
• vector_reproject

  Transform vector to different CRS with reflection

  Try:Reproject this vector to UTM zone 10NTry:Change the projection of these boundaries
• vector_convert

  Convert vector between different formats (SHP, GPKG, GeoJSON)

  Try:Convert this shapefile to GeoJSONTry:Change this GeoPackage to SHP format
• vector_clip

  Subset vector data spatially

  Try:Clip these boundaries to this extentTry:Extract features within this polygon
• vector_buffer

  Create buffer zones around vector geometries

  Try:Create a 1km buffer around these pointsTry:Buffer these lines by 500 meters
• vector_simplify

  Simplify geometries while preserving topology

  Try:Simplify these boundaries to reduce complexityTry:Reduce the detail in this coastline
• vector_query

  Perform spatial/attribute queries on vector data

  Try:Find all schools in this areaTry:Query for features where name equals 'Park'

Comparable tools

Installation

# Run directly from PyPI
uvx --from gdal-mcp gdal --transport stdio

{
  "mcpServers": {
    "gdal-mcp": {
      "command": "uvx",
      "args": ["--from", "gdal-mcp", "gdal", "--transport", "stdio"],
      "env": {
        "GDAL_MCP_WORKSPACES": "/path/to/your/geospatial/data"
      }
    }
  }
}

FAQ

What makes GDAL MCP different from other geospatial tools?

GDAL MCP's unique reflection middleware requires AI to justify methodological choices before execution, preventing silent failures and creating documented methodology for reproducible geospatial science.

How does the reflection caching system work?

The system caches epistemic reasoning about methodological decisions, achieving 75%+ hit rates when similar operations are repeated later. This knowledge persists across different data types (raster/vector) for efficiency.

Compare gdal-mcp with