QGISMCP - QGIS Model Context Protocol Integration

Name: QGISMCP - QGIS Model Context Protocol Integration
Author: jjsantos01

@jjsantos01

Repository

About QGISMCP - QGIS Model Context Protocol Integration

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

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "qgis": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/PARENT/REPO/FOLDER/qgis_mcp/src/qgis_mcp",
        "run",
        "qgis_mcp_server.py"
      ]
    }
  }
}

Tools

Simple ping command to check server connectivity

Get QGIS information about the current installation

Load a QGIS project from the specified path

Create a new project and save it

Get current project information

Add a vector layer to the project

Add a raster layer to the project

Retrieve all layers in the current project

Remove a layer from the project by its ID

Zoom to the extent of a specified layer

Retrieve features from a vector layer with an optional limit

Execute a processing algorithm with the given parameters

Save the current project to the given path

Render the current map view to an image file

Execute arbitrary PyQGIS code provided as a string

Overview

What is QGISMCP - QGIS Model Context Protocol Integration?

QGISMCP connects QGIS to Claude AI through the Model Context Protocol (MCP), enabling direct AI-driven project creation, layer management, processing algorithm execution, and custom Python code execution within QGIS.

How to use QGISMCP - QGIS Model Context Protocol Integration?

Install the QGIS plugin by copying the qgis_mcp_plugin folder into your QGIS profile plugins directory and enabling it via the Plugins manager. Configure Claude Desktop by adding the provided JSON block to claude_desktop_config.json, pointing to the qgis_mcp_server.py file. Start the server in QGIS from Plugins > QGIS MCP > QGIS MCP and click "Start Server". Claude will then have access to a set of tools to interact with QGIS.

Key features of QGISMCP - QGIS Model Context Protocol Integration

Two-way communication between Claude AI and QGIS via a socket-based server.
Create, load, and save QGIS projects programmatically.
Add and remove vector or raster layers from the project.
Execute processing algorithms from the Processing Toolbox.
Run arbitrary PyQGIS code from Claude (use with caution).
Render the current map view to an image file.

Use cases of QGISMCP - QGIS Model Context Protocol Integration

Create a new QGIS project and add multiple vector/raster layers using natural language.
Execute processing algorithms such as centroid calculation on vector layers.
Generate choropleth maps with custom classification and color ramps via PyQGIS.
Load an existing project, inspect layers, and retrieve feature data.
Automate map rendering and project saving through conversational commands.

FAQ from QGISMCP - QGIS Model Context Protocol Integration

What are the prerequisites for using QGISMCP?

QGIS 3.x, Claude Desktop, Python 3.10 or newer, and the uv package manager are required.

How do I install the QGIS plugin?

Download the repository, copy the qgis_mcp_plugin folder into your QGIS profile’s Python/plugins directory, then enable it in QGIS via Plugins > Installing and Managing Plugins.

How do I configure Claude Desktop?

Edit claude_desktop_config.json to include a new MCP server entry with command: "uv", and provide the absolute path to the directory containing qgis_mcp_server.py in the args.