NetLogo MCP
@Razee4315
The first MCP server for NetLogo, the most widely used agent-based modeling platform. Lets AI assistants create models with real interface widgets, run simulations and BehaviorSpace parameter sweeps, export world views as PNG, and safely run peer-reviewed models from the CoMSES Net library.
Overview
NetLogo MCP
The first MCP server for NetLogo, the most widely used agent-based modeling platform — taught in complexity science, ecology, economics, and social science courses worldwide.
What it does
- Create models with real interface widgets: sliders, switches, buttons, monitors, live plots
- Run simulations and collect tick-by-tick data from agents and patches
- BehaviorSpace parameter sweeps — headless, parallel experiment runs
- Export the world view as PNG, displayed inline in chat
- CoMSES Net integration — search and safely run models from the peer-reviewed model library
25 tools. GUI mode (watch the simulation live) and headless mode. Windows, macOS, and Linux.
Installation
pip install netlogo-mcp
Requires Python 3.10+, a NetLogo (https://ccl.northwestern.edu/netlogo/) installation, and a JDK 11+. Zero-config setup script and per-client configuration (Claude Code, Claude Desktop, Cursor, and more) in the README (https://github.com/Razee4315/NetLogo-MCP).
Example prompts
▎ Create a simple NetLogo model with 50 turtles doing a random walk. Run setup, simulate 100 ticks, and export the view.
▎ Open the Wolf Sheep Predation model and run a parameter sweep on initial-number-wolves from 10 to 100.
MIT licensed · GitHub (https://github.com/Razee4315/NetLogo-MCP) · PyPI (https://pypi.org/project/netlogo-mc
Server Config
{
"mcpServers": {
"netlogo": {
"command": "netlogo-mcp",
"args": [],
"env": {
"NETLOGO_HOME": "C:/Program Files/NetLogo 7.0.3",
"JAVA_HOME": "C:/Program Files/Eclipse Adoptium/jdk-25.0.2.10-hotspot"
}
}
}
}