Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Create, run, and analyze NetLogo agent-based models through natural conversation
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
NETLOGO_HOME, JAVA_HOME, NETLOGO_GUIYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"netlogo": {
"command": "uvx",
"args": [
"netlogo-mcp"
],
"env": {
"NETLOGO_HOME": "your-value",
"JAVA_HOME": "your-value",
"NETLOGO_GUI": "your-value"
}
}
}
}Run this in your terminal
claude mcp add netlogo --env NETLOGO_HOME=your-value --env JAVA_HOME=your-value --env NETLOGO_GUI=your-value -- uvx netlogo-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"netlogo": {
"command": "uvx",
"args": [
"netlogo-mcp"
],
"env": {
"NETLOGO_HOME": "your-value",
"JAVA_HOME": "your-value",
"NETLOGO_GUI": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"netlogo": {
"type": "stdio",
"command": "uvx",
"args": [
"netlogo-mcp"
],
"env": {
"NETLOGO_HOME": "your-value",
"JAVA_HOME": "your-value",
"NETLOGO_GUI": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
NETLOGO_GUI envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account Razee4315, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: NETLOGO_HOME, JAVA_HOME
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.0.2) reached the registry 5 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, NexusWindows
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Windows computer use in the background: desktop apps driven without your mouse or keyboard.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
The first MCP (Model Context Protocol) server for NetLogo — enabling AI assistants to create, run, and analyze agent-based models through natural conversation.
Works with: Claude Code, Claude Desktop, Cursor, Windsurf, VS Code (Copilot), Cline, Continue, Roo Code, Zed, OpenCode, Codex — any tool that supports MCP.
As an AI student taking an Agent-Based Modeling course, I searched for an MCP server to control NetLogo — nothing existed. So I built one.
Instead of manually writing NetLogo code, clicking buttons, and tweaking sliders, you tell your AI assistant what you want in plain English:
"Create a predator-prey model with 100 sheep and 20 wolves. Run it for 500 ticks and show me the population dynamics."
The AI writes the code, runs the simulation, and shows you the results — all through conversation.
By default a real NetLogo window opens (on first use) so you can watch your simulations run live. Headless mode is available for CI or servers.
See docs/TOOLS.md for the full reference of all 25 tools, widget schema, and prompts.
| Requirement | Install via terminal? | How |
|---|---|---|
| Python 3.10+ | Yes | Windows: winget install Python.Python.3.12 · macOS: brew install python@3.12 · Linux: sudo apt install python3.12 |
| Java JDK 11+ | Yes | Windows: winget install EclipseAdoptium.Temurin.21.JDK · macOS: brew install --cask temurin · Linux: sudo apt install openjdk-21-jdk |
| NetLogo 7.0+ | No — manual | Download from ccl.northwestern.edu/netlogo |
Only NetLogo requires manual download. Everything else can be installed via terminal, and the Zero-Config Setup prompt below handles those automatically.
If you're using an AI coding tool, copy the prompt below into your chat. The AI will detect your OS, find your NetLogo and Java installations, clone the repo, install dependencies, configure your MCP client, and tell you how to use it.
Click to copy the setup prompt
Please set up the NetLogo MCP server for me end-to-end. Follow these steps carefully:
C:/Program Files/NetLogo*/Applications/NetLogo*/opt/netlogo*, ~/netlogo* If NetLogo isn't installed, tell me to download it from https://ccl.northwestern.edu/netlogo/download.shtml and stop.pip install netlogo-mcpnetlogo-mcp command is now available on my PATH.netlogo server entry with:command: netlogo-mcpenv.NETLOGO_HOME: the NetLogo path you detectedenv.JAVA_HOME: the JDK path you detected"type": "stdio" for Cursor, "servers" key for VS Code)."Create a simple predator-prey model with wolves and sheep on a green landscape. Run setup, then run 100 ticks while tracking wolf and sheep counts. Export the view before and after so I can see how the world evolved."
models/ and exports/ folders) and that I can browse them with the list_models tool.Do not skip any verification step. If something fails, stop and tell me exactly what failed and how to fix it.
pip install netlogo-mcp
Then add the server to your MCP client. For Claude Code, add to your project's .mcp.json:
{
"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" } } } }
Restart Claude Code and verify with /mcp.
Tip: prefer project-scope config (
.mcp.jsonin one project) over global config — a global entry loads the server in every session of every project.
Using Cursor, Windsurf, VS Code, Cline, Continue, Roo Code, Zed, OpenCode, Codex, or Claude Desktop? See docs/CLIENTS.md for exact config for all 11 clients. All configuration options (GUI/headless mode, directories, limits) are in docs/CONFIGURATION.md.
Developing or contributing? Clone the repo and install editable instead:
git clone https://github.com/Razee4315/NetLogo-MCP.git
cd NetLogo-MCP pip install -e ".[dev]"
The image bakes in NetLogo (headless) with its bundled JRE — no host install needed:
docker build -t netlogo-mcp .
docker run -i --rm netlogo-mcp
MCP client config:
{
"mcpServers": { "netlogo": { "command": "docker", "args": ["run", "-i", "--rm", "netlogo-mcp"] } } }
Docker runs headless only (no GUI mode). Add -v ./exports:/data/exports to keep exported views and worlds on the host.
Once connected, try these prompts in any MCP client:
> 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.
Build a disease spread model with sliders for population size and
infection chance.
The first model tool call takes 30-60 seconds while the JVM starts — the NetLogo window appears when it's ready. Don't click stop. Every call after that is instant.
| Problem | Solution |
|---|---|
NETLOGO_HOME is not set | Set the environment variable to your NetLogo install directory |
JAVA_HOME is not set | Set it to your JDK directory (not JRE) |
| JVM crashes on startup | Make sure JAVA_HOME points to JDK 11+, not an older version |
No model is loaded | Call open_model or create_model before using other tools |
| First model call hangs for 30-60s | Normal — JVM is warming up. Don't click stop. |
| NetLogo window opens when my AI client starts | You have NETLOGO_EAGER_START=true set, or an old version — by default the window only opens on first tool use |
| Server won't connect | Run netlogo-mcp manually in terminal to see error output |
If you use NetLogo MCP in research or teaching, please cite it — click "Cite this repository" in the GitHub sidebar, or see CITATION.cff.
Saqlain Abbas Email: saqlainrazee@gmail.com GitHub: @Razee4315 LinkedIn: @saqlainrazee
This project is licensed under the MIT License — free to use, modify, and distribute for any purpose.