With ARES Commander 2027 Service Pack 2 or newer, you can connect ARES Commander to your favorite AI assistant, such as Claude Desktop (Anthropic), Claude Code (Anthropic), Devin Desktop (Cognition), Codex by ChatGPT (OpenAI), Google Antigravity (Google Gemini), or GitHub Copilot. This is done with the new ARES MCP Server. Once connected, you simply tell the AI assistant in plain language what you want, and it works directly in ARES Commander for you.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard that lets AI assistants talk to other programs in the same way.
Think of MCP like a USB plug for AI: instead of a special connection for every AI product, there is one standard connector. ARES Commander offers this connector to your favorite AI assistant (read further below).
What can I do with it?
The AI assistants connected via MCP can read your drawing, run commands, and check the result. Here are some examples of advanced CAD workflows using your AI assistant to create and modify DWG drawings in ARES Commander:
Use cases | What it demonstrates |
From an image to a 3D DWG model | Interpret an image and its dimensions to create real 2D and 3D CAD geometry |
Turn a floor plan image into a customizable DWG drawing | Recognize floor plan geometry, add dimensions and annotations, and create customizable blocks |
Design a kitchen automatically with parametric CAD blocks | Optimize a kitchen layout using reusable parametric blocks for furniture and appliances |
Create a parametric product configurator without programming | Learn from existing YouTube tutorials.
Create and customize advanced parametric CAD drawings.
|
Turn a PDF floor plan into an automated quantity takeoff | Convert PDF to DWG, analyze room areas, annotate drawings, and export quantities |
Georeferenced DWG survey from satellite imagery | Analyze satellite imagery, place scaled tree blocks, and generate terrain profiles from contour lines |
Turn a hand sketch into a 3D bridge and 2D drawings | Transform a hand-drawn concept into a 3D DWG model and generate 2D documentation |
Good to know
It runs on your computer: The connection between the AI assistant and ARES Commander stays on your own computer (localhost). You do not need to install extra software such as Python.
It works with many AI assistants: The same ARES MCP Server works with the desktop apps of OpenAI, Anthropic, Google, GitHub, and Cognition.
Windows, macOS and Linux versions of ARES Commander, ARES Mechanical, and ARES Electrical are supported (from version 2027 SP2).
What you need
ARES Commander 2027 SP2 or newer:
At least one AI assistant that supports MCP, for example, Claude Desktop app (Anthropic), Claude Code (Anthropic), Devin Desktop (Cognition), Codex by ChatGPT (OpenAI), or Google Antigravity (Gemini).
Step 1: Start the MCP server in ARES Commander
Open ARES Commander.
In the command line, type
MCPSTARTand press Enter.When asked for a port, press Enter to use the default port 19400.
Note: You need to run MCPSTART once each time you start ARES Commander. If ARES Commander is started automatically by your AI assistant, the server starts on its own.
These three commands help you control the server:
Command | What it does |
| Starts the MCP server. Asks for a port (default 19400). Tells you if the server is already running. |
| Stops the MCP server. |
| Shows if the server is running, and its port, running time, number of requests and number of connections. |
Step 2: Connect your AI assistant
Each AI assistant has its own settings file. In all cases you add one entry called ares that points to this address:
http://localhost:19400/mcp
Important: If your settings file already has content, do not delete it. Only add the ares entry inside the existing mcpServers section. In the paths below, replace <your-user-name> with your Windows user name.
Claude Desktop (Anthropic)
Open Claude Desktop.
Go to Settings → Developer.
Click Edit Config to open the configuration file.
Add this entry (if the file is empty, paste all of it):
{
"mcpServers": {
"ares": {
"command": "npx",
"args": ["-y", "mcp-remote", "http://localhost:19400/mcp"]
}
}
}Save the file.
Close Claude Desktop completely. On Windows, open the Task Manager and end any Claude processes that are still running.
Start Claude Desktop again and check under Settings → Developer that ares is listed and running.
Claude Code (Anthropic)
Open a terminal.
Run this command:
claude mcp add --scope user --transport sse ares http://localhost:19400/mcp
Start a new Claude Code session.
Type
/mcpto check that ares is listed and connected.
Devin Desktop (Cognition)
Open the file
mcp_config.jsonin this folder (create it if it does not exist):Windows:
C:\Users\<your-user-name>\.codeium\windsurf\macOS and Linux:
~/.codeium/windsurf/
Add this entry (if the file is empty, paste all of it):
{
"mcpServers": {
"ares": {
"type": "sse",
"url": "http://localhost:19400/mcp"
}
}
}Save the file and restart Devin Desktop.
Open a new Cascade chat with Ctrl + L and check in the MCP menu that ares is active.
Codex by ChatGPT (OpenAI)
Open the file
config.tomlin this folder (create it if it does not exist):Windows:
C:\Users\<your-user-name>\.codex\macOS and Linux:
~/.codex/
Add these lines:
[mcp_servers.ares]
url = "http://localhost:19400/mcp"
enabled = trueSave the file and restart Codex (or open a new session).
Google Antigravity (Google Gemini)
Open the file
settings.jsonin this folder:Windows:
C:\Users\<your-user-name>\.gemini\macOS and Linux:
~/.gemini/
Add this entry inside the file:
"mcpServers": {
"ares": {
"type": "sse",
"url": "http://localhost:19400/mcp"
}
}Save the file, restart Google Antigravity and open a new session.
Check that ARES is listed as an active MCP server.
GitHub Copilot, the alternative if you are using Microsoft Copilot or want to use multiple AI assistants
GitHub Copilot functions as a multi-model ecosystem, giving you the flexibility to choose your preferred AI vendor rather than locking you into one. While it doesn’t integrate with the consumer-facing Microsoft Copilot application, it lets you connect with this AI assistant and switch fluidly between industry-leading foundational models from OpenAI (Codex by ChatGPT), Anthropic (Claude Code in Claude Desktop), and Google Gemini (Antigravity) right inside your development environment.
It is therefore the recommended approach if you want to use Microsoft Copilot with ARES Commander, but also a nice alternative if you want to use multiple AI assistants from different providers.
ARES is available as a local MCP server at http://localhost:19400/mcp.
Start the ARES service and confirm it is listening on port 19400.
In GitHub Copilot, open Customize → Installed and add a custom MCP server.
Enter:
Name:
ARESURL:
http://localhost:19400/mcp
4. Save the server and verify that its tools are available to Copilot.
Alternative method to connect ARES MCP with GitHub Copilot via configuration file:
Navigate to
C:\Users\<your-user-name>\.copilot\on Windows
or~/.copilot/if you are on macOS or LinuxOpen the
mcp-config.jsonfile. If it doesn't exist, create it.Add the following configuration:
{ "mcpServers": { "ares": { "tools": [ "*" ], "type": "http", "url": "http://localhost:19400/mcp" } } }4. Save the file and restart GitHub Copilot.
5. Make sure the ARES MCP server is running, then verify that its tools are available in GitHub Copilot.
Step 3: Test the connection
Make sure ARES Commander is open and
MCPSTARThas been run.Open a new chat in your AI assistant and make sure the ARES MCP server is enabled.
Type this prompt: Draw a circle at 200,200 with radius 50
If a circle appears in ARES Commander, everything works. 🎉
Example prompts to try
"Draw a 200 x 120 plate with a 10 mm hole in each corner, 15 mm from the edges, and zoom to fit."
"Give me an overview of this drawing: which layers are used, how many blocks, and are any references missing?"
"Check this drawing before I send it out: is everything dimensioned and is all text readable?"
"Replace 'Rev A' with 'Rev B' in all text, and move every circle to layer HOLES."
"Save this as plate_revB.dwg in the same folder and give me a picture of it."
More sophisticated prompts to try with MCP:
Prompt to modify a floor plan that contains a dynamic block for a window (via MCP)
The wall along the top of the drawing is an exterior wall with a total thickness of 40 cm. The same applies to the wall on the right, which contains the window. The window opens inward, with the hinges on the right-hand side.
More detailed prompt to modify your floor plan via MCP
Modify the current drawing in ARES Commander by moving the shared wall between Bedroom 1 and Bedroom 2 exactly 100 cm (1 meter) to the left.The goal is to increase the usable floor area of both bedrooms while preserving the overall architectural layout as much as possible.Requirements:
Move the entire shared wall 100 cm to the left, maintaining its original orientation, thickness, and alignment.
Adjust the geometry of both bedrooms accordingly to create more usable space.
Preserve the external walls, doors, windows, and all other existing architectural elements unless a modification is strictly necessary.
Ensure that both bedrooms remain functional, with adequate circulation and access through their existing doors.
Check for overlapping geometry, gaps, or inconsistencies after moving the wall.
Update any affected dimensions, room labels, and areas if they are included in the drawing.
Important: Work directly on the existing drawing, changing only what is necessary to achieve this modification. Before making any additional design changes, ask me for approval.When finished, verify that the shared wall has moved exactly 100 cm to the left and save the modified drawing under a new filename, keeping the original file unchanged.
Example of prompt to design a kitchen via MCP:
Next, I want you to plan the kitchen units, taking into account the available cabinet sizes and the appliances we need to accommodate. We will use standard base units, typically 60 cm wide, as well as 90 or 100 cm units for cabinets with doors or drawers. The manufacturer also offers 40 cm and 50 cm-wide tall units for additional storage.
We need a 60 cm-wide tall unit to accommodate the oven and microwave, as well as another tall unit with the washing machine and dryer stacked vertically. We also need a 90 cm-wide double-door refrigerator and a dishwasher. The sink can be an undermount model without a draining board, and the cooking area should include a ceramic glass cooktop.
Create dynamic blocks for the kitchen furniture and appliances, and add two sections to help us understand how the units should be arranged.
What the AI assistant can do in ARES Commander
Area | What the assistant can do |
Session | Check that ARES Commander is ready and get version information. |
Commands | Run any ARES command, LISP expressions and macros. List the available commands. |
Read the drawing | Get a summary, layers, blocks, external references, entities and their properties, dimensions, text, the current selection and the undo history. |
Change the drawing | Change entity properties, edit text, create multiline text and select entities. |
Drawings | List open drawings, switch between them, save under a new name and check the saved file. |
Quality checks | Validate the drawing, find parts without dimensions, and find overlapping or too small annotations. |
View | Zoom, read view and viewport information, and save the view as a PNG image. |
System variables | Read and change system variables. |
User interface | Find and press buttons, fill in fields, use shortcuts and context menus, and take screenshots. |
Built-in safety
You stay in control when saving: ARES Commander asks you to confirm before the AI assistant saves a drawing under a new name.
No interruptions: The AI assistant cannot start a new command while another command is still running.
Can I use the MCP connectors with the web version of my AI assistant, i.e., ChatGPT, Claude Chat, Cowork, Gemini, and/or Microsoft Copilot?
For technical reasons, the MCP connectors for ARES Commander are built to work with the desktop clients of your favorite AI assistant. These Desktop versions are part of your subscription when you use an AI assistant. You just need to use the right tool:
For OpenAI: Use Codex by ChatGPT (included in ChatGPT Desktop) instead of ChatGPT web version (chatgpt.com)
For Anthropic: Use Claude Code (included in Claude Desktop) instead of the web version (claude.ai)
For Gemini: Use Google Antigravity (Desktop app + Google Antigravity agy CLI) instead of web version of Gemini (gemini.google.com)
For Microsoft Copilot: Use GitHub Copilot. The desktop version doesn't include the features to enable MCP integration with desktop solutions like ARES Commander.
Note: MCP connectors for the web versions of these AI assistants will be gradually released in our online version ARES Kudo in the coming months. The MCP Server feature also planned for in ARES Mechanical and ARES Electrical!
Troubleshooting
The AI assistant cannot connect: Type
MCPSTATUSin ARES Commander. If the server is not running, typeMCPSTART.The ARES server does not show up in the AI assistant: Check the settings file for typing errors (missing commas or brackets), save it and restart the AI assistant completely.
Other MCP servers stopped working: You may have overwritten your settings file. Add your other servers back next to the ares entry.
Port already in use: Run
MCPSTARTwith a different port, and use the same port in the address in your AI assistant settings.
