Complete AI Training

MCP server · Coding

AgentFEM MCP server

by haoming-luo

Lets your AI set up, run and check finite-element simulations through AgentFEM, with the results kept visible.

Flow diagram: you ask your AI “Create and run a 2D cantilever simulation”, on your own computer the AgentFEM MCP server works with agentFEM, and you get back simulation result summary.

AgentFEM MCP is a small helper that connects your AI assistant to AgentFEM, a program that runs finite-element simulations. Finite-element simulations are the computer models engineers use to see how a part bends, heats up or holds a load. It is handy if you already use AgentFEM and want your AI to help you build, run and read those simulations without clicking through everything by hand.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to another tool. This one connects your AI to AgentFEM, the simulation engine on your computer. Once it is set up, you can ask your AI in plain words to create a simulation project or run one, and the helper passes that request to AgentFEM for you.

What this MCP server does

You ask your AI something like create a 2D cantilever and run it. The AI uses this helper to start a new project from an AgentFEM template inside a folder you approved. The helper then asks AgentFEM to check the project and run the simulation in the background. When it finishes, the helper reads back a short summary of the result, and the AI explains it to you in the chat.

Flow diagram: you ask your AI “Create and run a 2D cantilever simulation”, on your own computer the AgentFEM MCP server works with agentFEM, and you get back simulation result summary. Click to zoom

What you can do with it

  • Create a new simulation project from a ready-made AgentFEM template
  • Check a project for problems before you run it
  • Start a simulation run and watch its progress
  • Read a short summary of the result and how trustworthy it is
  • Look up which AgentFEM version and features are installed
  • Inspect a project and its recent runs to see what was done

Try asking your AI

  • “Use AgentFEM to create, validate, run and briefly explain a 2D cantilever. Keep the project and result paths visible.”
  • “Show me which AgentFEM version is installed and what it can do.”
  • “Check my project in the AgentFEMProjects folder for problems before I run it.”
  • “Start the simulation for my last project and tell me when it is done.”

What it gives back to you

You get short, readable answers in the chat: a project path, a pass or fail from the check, a run status, and a compact result summary with a note on how trustworthy it is. If you need the full evidence, the AI can ask for it separately. The helper does not dump raw solver files on you unless you ask.

Before you start

What you need

  • AgentFEM already installed on your computer
  • Python and the uvx tool, or the agentfem-mcp package installed with pip
  • A folder you approve for projects, set in AGENTFEM_MCP_ROOTS
  • An MCP-compatible app such as Codex, Claude Desktop, Claude Code or VS Code

Good to know

It can start real simulation runs on your computer, so point it at one project folder you are happy to have changed, not your whole home directory.

Install it with your AI

Add AgentFEM MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check AgentFEM MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

Engineers, researchers and students who already run AgentFEM simulations and want their AI assistant to help set up, run and read them.