# jjsantos01/qgis_mcp

Model Context Protocol (MCP) that allows LLMs to use QGIS Desktop

Repository: https://github.com/jjsantos01/qgis_mcp
Canonical: https://ross.abutalabs.com/products/qgis_mcp
Language: Python
License Family: other
Last push: 2025-10-01T01:23:25+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 44, release rhythm 35, longevity 38
- inputs: {"age_days": 539, "days_push": 337, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1072, forks 169 (observed 2026-08-28T04:03:28.138651+00:00)

## What it is
A Model Context Protocol integration that lets LLMs like Claude control QGIS Desktop via a socket-based QGIS plugin and an MCP server. It supports project and layer manipulation, running processing algorithms, and executing arbitrary Python code inside QGIS.

## Use cases
- control qgis with claude ai
- create gis projects from natural language prompts
- add and remove vector or raster layers via llm
- run qgis processing toolbox algorithms from a chatbot
- execute python code in qgis through an ai assistant
- prompt-assisted geospatial analysis in qgis

## When to choose
- you use QGIS Desktop and want LLM-driven automation
- you want Claude to create projects, load layers, or run processing algorithms
- you need arbitrary Python execution inside QGIS from an AI assistant

## When to avoid
- you need a production-grade, security-hardened integration (arbitrary code execution is risky)
- you use QGIS Server or web-based GIS instead of QGIS Desktop
- you need a licensed/supported tool rather than an experimental community project

## Facets
- artifact type: plugin
- maturity: active
- function: mcp, agent-framework, plugin-system, developer-tools
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform, windows
- tags: qgis, gis, claude, llm-integration, socket-server, geospatial, ai-agents, maps, desktop, macos, linux

## Member repositories
- jjsantos01/qgis_mcp (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:28.138651+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:42.059229+00:00, confidence not recorded.
  - readme: https://github.com/jjsantos01/qgis_mcp (fetched 2026-08-28T04:03:28.138651+00:00, sha 38985b173364)
- Data as of 2026-08-30T08:39:29.467469+00:00.