QGIS MCP Server Integration

What does “QGIS” MCP Server do?

The QGIS MCP Server is a Model Context Protocol (MCP) implementation that bridges QGIS Desktop with large language models (LLMs), such as Claude. By leveraging a socket-based server and the QGIS MCP plugin, it enables AI assistants to directly control and interact with QGIS projects. This allows AI-driven automation of tasks like project creation, layer manipulation, algorithm execution via the Processing Toolbox, and even direct Python code execution within QGIS. The server is designed to streamline geospatial workflows, facilitate advanced data processing, and enhance developer productivity by enabling seamless, prompt-assisted management of QGIS from an LLM client.

List of Prompts

No explicit prompt templates are mentioned in the repository.

List of Resources

No explicit MCP resources are described in the repository.

List of Tools

• Project Manipulation: Allows creating, loading, and saving QGIS projects via LLM commands.
• Layer Manipulation: Enables adding or removing vector and raster layers in a QGIS project.
• Execute Processing: Runs QGIS processing algorithms (from the Processing Toolbox) through an LLM interface.
• Code Execution: Executes arbitrary Python code within the QGIS environment via LLM requests. (Highly powerful, use with caution.)

Use Cases of this MCP Server

• Automated Project Creation: Developers and data scientists can use LLMs to automate the setup of new QGIS projects, ensuring consistent structure and configuration.
• Geospatial Data Layer Management: LLMs can programmatically add, remove, or update vector and raster layers, streamlining data ingestion and visualization workflows.
• Batch Processing via Algorithms: AI assistants can trigger complex QGIS Processing Toolbox algorithms on large datasets, saving time and reducing manual intervention.
• Remote Code Execution: Users can send Python scripts to be executed within QGIS, facilitating custom analysis, data transformation, or plugin development.
• AI-Assisted Geospatial Analysis: By exposing QGIS functions to LLMs, advanced spatial queries and map operations can be conducted conversationally or through AI agents.

How to set it up

Windsurf

No setup instructions found for Windsurf.

Claude

1. Prerequisites: Ensure QGIS 3.X (tested on 3.22), Python 3.10+, and the uv package manager are installed.
2. Download the Repository:

   git clone git@github.com:jjsantos01/qgis_mcp.git
   

3. Install QGIS Plugin:
   • Copy the qgis_mcp_plugin folder to your QGIS profile plugins folder (see README.md for platform-specific locations).
   • Restart QGIS and enable the “QGIS MCP” plugin.
4. Edit Claude Configuration:
   • Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json.
   • Add the following under mcpServers:

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

5. Save and Restart Claude to apply the configuration.

Securing API Keys

No API or environment variable usage for keys is described in the repo.

Cursor

No setup instructions found for Cursor.

Cline

No setup instructions found for Cline.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "qgis": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “qgis” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between the two tables, the QGIS MCP Server is well-documented in terms of core features and tool exposure, but lacks explicit prompt/resource listings and does not cover API key security or sampling/roots support. I’d rate it a 6/10 for MCP completeness and developer readiness.

MCP Score