GDAL
Model Context Protocol server that packages GDAL-style geospatial workflows through Python-native libraries (Rasterio, GeoPandas, PyProj, etc.) to give AI agents catalog discovery, metadata intelligence, and raster/vector processing with built-in rea
What is GDAL?
GDAL is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that packages gdal-style geospatial workflows through python-native libraries (rasterio, geopandas, pyproj, etc.) to give ai agents catalog discovery, metadata intelligen...
Model Context Protocol server that packages GDAL-style geospatial workflows through Python-native libraries (Rasterio, GeoPandas, PyProj, etc.) to give AI agents catalog discovery, metadata intelligence, and raster/vector processing with built-in rea
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Protocol server that packages GDAL-style geosp
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx gdalConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use GDAL
The GDAL MCP server packages GDAL-style geospatial workflows through Python-native libraries — Rasterio, GeoPandas, and PyProj — and exposes them as MCP tools that AI agents can call directly. It provides raster operations (info, convert, reproject, stats, query) and vector operations (info, convert, clip, buffer, simplify, query) alongside catalog discovery and metadata resources. Geospatial researchers, GIS analysts, and earth observation engineers can use it to let Claude process satellite imagery, shapefiles, and other geographic datasets without writing any GDAL command-line scripts.
Prerequisites
- Python 3.10+ and uv package manager installed
- The gdal-mcp package available on PyPI (install via uvx)
- Geospatial data files accessible from the server host (rasters, shapefiles, GeoJSON, etc.)
- An MCP-compatible client such as Claude Desktop
- Optional: Docker if you prefer the containerized deployment
Install the server via uvx
The recommended approach is to run gdal-mcp directly with uvx, which installs it into an isolated environment automatically. No manual pip install needed.
uvx --from gdal-mcp gdal --transport stdioSet the workspace security variable
Set GDAL_MCP_WORKSPACES to a colon-separated list of directories the server is allowed to read. If unset, all paths are allowed — restrict this in production.
export GDAL_MCP_WORKSPACES=/path/to/your/geodata:/another/data/dirEnable specific tool surfaces (optional)
By default both raster and vector tools are available. You can explicitly enable only the ones you need with environment flags.
export RASTER=true
export VECTOR=trueConfigure Claude Desktop
Add the server to your claude_desktop_config.json. The GDAL_MCP_WORKSPACES env var tells the server which directories it may access.
{
"mcpServers": {
"gdal-mcp": {
"command": "uvx",
"args": ["--from", "gdal-mcp", "gdal", "--transport", "stdio"],
"env": {
"GDAL_MCP_WORKSPACES": "/path/to/your/geospatial/data"
}
}
}
}Restart Claude Desktop and test
Restart your MCP client. Ask Claude to list available datasets or query metadata from a raster file in your workspace directory to verify the connection.
GDAL Examples
Client configuration (Claude Desktop)
Place this in your claude_desktop_config.json. Adjust the GDAL_MCP_WORKSPACES path to point to a directory containing your geospatial files.
{
"mcpServers": {
"gdal-mcp": {
"command": "uvx",
"args": ["--from", "gdal-mcp", "gdal", "--transport", "stdio"],
"env": {
"GDAL_MCP_WORKSPACES": "/Users/yourname/geodata",
"RASTER": "true",
"VECTOR": "true"
}
}
}
}Prompts to try
Ask Claude to inspect, transform, and analyze geospatial files in your workspace directory.
- "Get metadata and CRS info for the file elevation.tif in my geodata folder"
- "Reproject the shapefile roads.shp from EPSG:4326 to EPSG:3857"
- "Clip the vector file parcels.geojson to the bounding box of my study area"
- "Compute raster statistics (min, max, mean) for the satellite image ndvi.tif"
- "Convert the GeoTIFF dem.tif to a GeoPackage format"Troubleshooting GDAL
Server warns 'all paths are allowed' on startup
Set the GDAL_MCP_WORKSPACES environment variable to one or more colon-separated directory paths you want the server to access. This is a security measure — leaving it unset permits access to any path on the filesystem.
Tool calls return errors about missing GDAL or Rasterio libraries
The uvx command should install all Python dependencies automatically. If you see missing library errors, try running 'pip install gdal-mcp' in a fresh virtual environment to confirm the geospatial dependencies (Rasterio, GeoPandas, PyProj) resolve correctly on your OS.
Raster or vector tools are not available in the tool list
Ensure RASTER=true and VECTOR=true are set in the env block of your MCP config. By default these surfaces should be on, but explicit flags guarantee they are enabled.
Frequently Asked Questions about GDAL
What is GDAL?
GDAL is a Model Context Protocol (MCP) server that model context protocol server that packages gdal-style geospatial workflows through python-native libraries (rasterio, geopandas, pyproj, etc.) to give ai agents catalog discovery, metadata intelligence, and raster/vector processing with built-in rea It connects AI assistants to external tools and data sources through a standardized interface.
How do I install GDAL?
Follow the installation instructions on the GDAL GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with GDAL?
GDAL works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is GDAL free to use?
Yes, GDAL is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
GDAL Alternatives — Similar Data Science & ML Servers
Looking for alternatives to GDAL? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up GDAL in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use GDAL?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.