Skip to content
Tresca

PyCFX-MCP (Ansys CFX-MCP)

MCP serverOfficial · Pre-1.0

Ansys's own MCP server for CFX: drives CFX-Pre, CFX Solver and CFD-Post sessions through PyCFX with seven compact tools. By Ansys (Synopsys).

3 starsUpdated 1 day agoGitHub data from 5 Nov 2026

At a glance

Type
MCP server
Works with
Ansys Fluent / CFX
How it connects
Drives a running copy of the tool
Access
Can modify models
Tool versions
Any licensed Ansys CFX install that PyCFX (ansys-cfx-core) supports; not stated in the README
Operating systems
Not stated in its documentation
Needs a Ansys Fluent / CFX licence
Yes
Transport
Local (stdio), Remote (HTTP)
AI clients documented
VS Code (GitHub Copilot), Claude Desktop, Cursor
Licence
Apache-2.0
Language
Python
Release status
pre 1 0

What it can do

  • Starts or attaches to CFX-Pre, CFX Solver and CFD-Post, and reports session status.
  • Routes common setup, solve and post-processing actions through a single cfx_workflow tool.
  • Returns bounded model context (summaries, named objects, API help, allowed values) instead of dumping a whole model into the chat.
  • Validates and runs reviewed PyCFX snippets in a persistent context with guarded imports.

Limitations

  • Version 0.2.0 on PyPI; still pre-1.0.
  • Needs Python 3.12 to 3.14 and a licensed local CFX install for every live-session tool.
  • The code sandbox is Python-level only, not an operating-system or container sandbox, and HTTP should only be used on trusted networks.

Install

pip install ansys-cfx-mcp
ansys-cfx-mcp --transport stdio

Source: github.com/ansys/pycfx-mcp

MCP servers and skills run code on your computer. Review the source before installing.

AI-generated models, drawings and results must be checked by a qualified engineer before use.