Whfkl

Whfkl / Abaqus-Control-MCP

Public

让 AI 可以驱动 Abaqus建模。Connect Claude, Cursor, and other MCP clients directly to your active Abaqus/CAE session.

20
2
85% credibility
Found May 20, 2026 at 20 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Abaqus Control MCP is a bridge that lets engineers control Abaqus simulation software using natural language through AI assistants like Claude or Cursor. Instead of writing code, users describe what they want (geometry, materials, loads, steps), and the AI translates those descriptions into actions that run directly in a live Abaqus session. Everything stays local on the user's machine, and the Abaqus window remains interactive so engineers can inspect progress at any time. The tool provides tools for checking connectivity, running Python code, monitoring job progress, and capturing viewport screenshots.

How It Works

1
🔧 You discover a smarter way to work with simulation software

An engineer learns they can describe what they want to build and have an AI assistant create it directly in their Abaqus window, without writing code by hand.

2
📦 You install the bridge that connects everything

You run a simple installation command, and the tool automatically sets up a small helper inside your Abaqus program alongside a connection point for your AI assistant.

3
▶️ You start Abaqus and activate the bridge

Inside Abaqus, you click a menu button to start the connection, and a small indicator confirms everything is listening and ready to receive instructions.

4
🤖 You tell your AI assistant what you want to build

You type something like 'create a rectangular plate with steel material and fixed edges' and watch as your AI assistant translates your words into actions happening live in your Abaqus window.

5
👀 You watch your model take shape in real-time

Geometry appears, materials get assigned, and everything updates right before your eyes while your Abaqus session stays fully interactive and responsive.

✅ Your simulation project is ready to run

Your complete model is built exactly as you described, saved in your working folder, and ready for analysis — all without touching a single line of code yourself.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 20 to 20 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Abaqus-Control-MCP?

Abaqus-Control-MCP is a bridge that lets AI assistants like Claude and Cursor drive Abaqus directly in your active modeling session. You describe what you want in plain language, and the AI executes Python code through Abaqus's API to build geometry, apply loads, set up steps, and monitor results. The system runs locally as a TCP server on your machine, exposing tools for running arbitrary Python, monitoring job status, inspecting ODB files, and capturing viewport screenshots.

Why is it gaining traction?

The hook is obvious: engineers spend hours fighting Abaqus's notoriously clunky GUI, and this lets them delegate that work to an AI that can actually touch their model. Unlike exporting scripts or writing batch files, you stay inside the live session, watching geometry and results update in real time. The structured error handling is genuinely useful—it doesn't just throw exceptions; it parses tracebacks, suggests nearby API methods, and shows available keys when you hit a KeyError.

Who should use this?

Simulation engineers automating repetitive workflows in Abaqus will get the most value. If you're building parametric studies, running optimization loops, or just tired of clicking through the same material assignment dialogs for the hundredth time, this removes friction. Researchers prototyping finite element models quickly will also benefit—the AI can scaffold geometry and mesh settings while you focus on physics.

Verdict

At 20 stars and v0.1.0, this is early-stage software with a credibility score of 0.85%—solid concept but unproven at scale. Documentation is clear and setup is straightforward, but test coverage and community activity are essentially nonexistent. Worth exploring if your workflow fits, but don't trust it with production analyses until it matures.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.