QGIS MCP
Related Servers
Alternatives to QGIS MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceConnects AI assistants (Claude, Cursor, etc.) to QGIS 4.x via MCP, enabling natural language-driven GIS workflows through 37+ tools, including data loading, processing, and spatial analysis.GPL 2.0
- AlicenseBqualityDmaintenanceA Model Context Protocol server that connects Claude AI to QGIS, enabling direct interaction with the GIS software for project creation, layer manipulation, code execution, and processing algorithms through natural language prompts.1510Creative Commons Zero v1.0 Universal
- AlicenseBqualityDmaintenanceA comprehensive MCP server providing 30 tools for geocoding, routing, and OpenStreetMap data analysis. It enables AI assistants to search for locations, calculate travel routes, and perform quality assurance checks on map data.3078 npm5MIT
- AlicenseNot gradedqualityDmaintenanceA geospatial MCP server that provides tools for geocoding, routing, elevation profiles, and spatial analysis. It enables AI agents to process GIS file formats like GeoJSON and Shapefiles while performing complex coordinate transformations and distance calculations.4MIT
- AlicenseNot gradedqualityBmaintenanceDeploy QGIS in Docker as an MCP server, enabling AI assistants to perform spatial analysis, data loading, cartography, and multi-format export without local installation.11MIT
- AlicenseAqualityCmaintenanceConnect QGIS to Claude AI through the Model Context Protocol (MCP), enabling Claude to directly control QGIS — manage layers, edit features, run processing algorithms, render maps, and more.1001MIT
TDQS
Scored across 125 tools
Most tools target a distinct resource and action, and descriptions actively disambiguate near-pairs like render_map vs get_canvas_screenshot and execute_sql vs execute_connection_sql. The sheer 125-tool surface still creates some selection friction, e.g. get_layers/find_layer/get_layer_tree and several expression-related tools, though each is arguably distinct.
The dominant pattern is verb_noun in snake_case (add_raster_layer, set_canvas_extent, list_processing_algorithms), which is highly consistent across the set. Minor deviations like ping, diagnose, raster_calculator, field_calculator, and zonal_statistics break the pattern, but they are readable and do not cause confusion.
At 125 tools, this is far beyond the well-scoped 3-15 tool range and falls into the 50+ extreme category. Even for a broad GIS desktop application, this many MCP tools creates a heavy selection and discovery burden for agents.
The tool surface is remarkably comprehensive: project lifecycle, vector/raster editing, styling, processing algorithms/background jobs/models, print layouts, SQL connections, expressions, bookmarks, and themes are all covered. Minor lifecycle gaps exist (e.g. no remove_layout_item, no delete_connection, no delete_processing_model), but execute_code and the general breadth make these workarounds rather than dead ends.