Control QGIS with an LLM to build projects, load layers, and run geospatial tasks.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "QGIS MCP" yet — see the docs or source repo.
Create a new QGIS project with WGS84, load local roads.geojson and buildings.geojson, and apply basic styling based on layer type.
A QGIS project with the coordinate system set, layers loaded, and initial styling applied.
Write and run a processing script in the current QGIS project to count points of interest within each district and save the result as a new layer named poi_count_by_district.
A working QGIS processing script is produced and executed, creating a new layer with the aggregated results.
Load all Shapefile and GeoPackage layers from the data folder into QGIS, group them by data source, and check whether any layers are missing a coordinate reference system.
All layers are batch loaded and organized, with a report of any layers missing a coordinate reference system.
Let AI control QGIS for spatial analysis, styling, and map export.
Deploy QGIS via Docker for AI-powered spatial analysis and map export.
Control dynamic maps and layers to visualize geospatial data in AI workflows.
Manage GeoServer REST API tasks and spatial service configuration with natural language.
Use full Git operations through MCP to manage repositories and collaboration.
Connect to Jupyter via MCP to run code and explore data interactively.