Skip to main content
Glama
Sign In
Ansys CFX-MCP

Ansys CFX-MCP

Official
by ansys
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Ansys CFX-MCP

PyAnsys Python Apache

Ansys CFX-MCP (ansys-cfx-mcp) is a Model Context Protocol (MCP) server that enables AI assistants to interact with Ansys CFX through PyCFX. It enables natural-language-assisted CFX-Pre, CFX Solver, and CFD-Post workflows for setup, execution, and postprocessing.

It is built on PyAnsys Common MCP (ansys-common-mcp), the shared PyAnsys MCP foundation.

This package is self-contained and works as a standalone server for any MCP host. It exposes a compact CFX-oriented tool surface so you can connect to CFX sessions, inspect bounded model context, validate and run reviewed PyCFX snippets, and coordinate common solver and CFD-Post actions.

For quick-start, configuration, architecture, examples, and per-tool reference material, see the PyCFX-MCP documentation.

Overview

Ansys CFX-MCP is a stateless MCP leaf. MCP clients such as Visual Studio Code Copilot, Claude Desktop, Cursor, or a custom automation host call a focused set of tools to drive live CFX-Pre, CFD-Post, and CFX Solver sessions. Custom Python runs through a validated, Python-level restricted execution path. This is not an operating-system or container sandbox.

Key features:

  • CFX session management: Start or attach to CFX-Pre, CFX Solver, and CFD-Post workflows.

  • Workflow routing: Use one compact cfx_workflow tool for common CFX lifecycle actions.

  • Bounded model context: Inspect summaries, named objects, API help, allowed values, and selected state snippets without dumping entire models into an MCP client.

  • Validated execution: Run custom snippets in a persistent PyCFX execution context with strict AST validation, guarded imports, and limited built-in functions.

  • Flexible MCP transport: Run over STDIO for local clients or Streamable HTTP for trusted local integrations.

Related MCP server: Mechanical MCP Server

Tool surface

The default MCP surface includes seven tools:

Group

Tools

Connection and session

connect, disconnect, and session_status

CFX workflow routing

cfx_workflow

Bounded model context

cfx_model_context

Code execution

run_code and validate_code

The server also exposes a toolsets://definition MCP resource for clients or conductors that group related tools. The default CFX toolsets cover connection management, CFX workflow routing, CFX model context, and code execution.

Requirements

Requirement

When needed

Notes

Python 3.12 or later

Always

3.12, 3.13 and 3.14 are supported

Core runtime dependencies

Always (installed automatically)

ansys-common-mcp, fastmcp, pydantic, and requests

A licensed local Ansys CFX installation

To launch or attach CFX tools

Required for workflows that use CFX-Pre, CFX Solver, or CFD-Post

PyCFX and Ansys CFX are required for live-session tools. Any tool that touches a CFX app (connect, run_code, cfx_workflow, cfx_model_context, and session_status) requires ansys-cfx-core and a licensed CFX installation on your machine.

Installation

Install the latest release for users:

pip install ansys-cfx-mcp

Install the latest release for developers:

git clone https://github.com/ansys/pycfx-mcp.git
cd pycfx-mcp
pip install -e ".[dev,doc]"

Usage

Run PyCFX-MCP over STDIO, the default transport for desktop MCP clients:

ansys-cfx-mcp --transport stdio

Or, run PyCFX-MCP over Streamable HTTP:

ansys-cfx-mcp --transport http --host 127.0.0.1 --port 8000

Use STDIO for desktop MCP clients that launch the server process. Use Streamable HTTP only on trusted networks or behind infrastructure that provides authentication and TLS.

Starting PyCFX-MCP only makes the tools available. You still need an MCP-compatible client, such as Visual Studio Code Copilot, Claude Desktop, Cursor, or another assistant host, to connect to PyCFX-MCP. For more information, see IDE and client configuration in the PyCFX-MCP documentation.

Configuration

The standalone server does not call a language model. Configure only the server transport, logging, and backend options needed for your MCP client. Custom code authoring belongs in the MCP host or a higher-level agent layer; PyCFX-MCP validates and runs reviewed Python through validate_code and run_code.

For transport settings, see Configuration in the PyCFX-MCP documentation.

License

This project is licensed under the Apache License, Version 2.0. See the LICENSE file for details.

Resources

For general PyAnsys questions, email pyansys.core@ansys.com.

Available Tools

7 tools
cfx_model_contextA

Return a targeted, compact CFX model context slice. Actions: summary, list_named_objects, find_named_object, select_named_objects, state, api_help, find_api, allowed_values, targeted_context. Use max_items to keep responses small.

Inputs: action, params, max_items. Returns: object

cfx_workflowA

Run one focused CFX lifecycle or artifact action. Actions: start_pre, import_mesh, write_def, start_solver, wait_solver, get_results_file, open_post, status. Use the external agent layer for custom PyCFX code generation.

Inputs: action (required), params. Returns: object

connectA

Connect the cfx leaf to a backend. Available backend kinds: ['pycfx']. Pass backend_kind to choose, or omit it to auto-select. Backend-specific options (url/token/ip/port/...) go in connect_kwargs as a dict and are forwarded to the backend.

Inputs: backend_kind, connect_kwargs. Returns: Result returned by the connection tool.

disconnectA

Disconnect the cfx leaf's active backend.

Inputs: no named parameters. Returns: object

run_codeA

Execute Python code against the active PyCFX session namespace. The code runs with pre, solver, post, session, cfxpre, cfxsolver, and cfxpost helpers refreshed from the current CFX sessions. Returns stdout, stderr, and any __return__ value. Prefer cfx_workflow or cfx_model_context for routed actions and read-only queries.

Inputs: code (required).

session_statusA

Report whether the cfx leaf has an active backend. Safe to call before connect. Returns the connected endpoint, backend kind, and the list of tools available in the current state.

Inputs: no named parameters. Returns: Result of `session_status` - safe to call before `connect`.

validate_codeA

Dry-run / validate CFX Python without applying side effects. Returns parse / type / semantic feedback.

Inputs: code (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools have clearly distinct roles: connection lifecycle (connect/disconnect/session_status), code execution/validation (run_code/validate_code), workflow actions, and model context queries. The main potential confusion is between run_code and cfx_workflow, since cfx_workflow actions could also be performed via custom Python, but the descriptions provide enough routing guidance to separate them.

    Naming Consistency4/5

    Tool names mostly follow a clean snake_case pattern with imperative verbs (connect, disconnect, run_code, validate_code). session_status and cfx_workflow/cfx_model_context are more noun-like, but overall the naming is consistent enough and predictable across the set.

    Tool Count5/5

    Seven tools is a well-scoped size for this server's purpose. Each tool covers a distinct functional layer: backend connection, live code execution, validation, high-level workflow control, and model introspection, without redundancy or bloat.

    Completeness4/5

    The tool surface covers the main CFX interaction lifecycle: connect, run custom code, validate, drive workflows, and inspect model context. run_code provides an escape hatch for arbitrary PyCFX operations, though a few high-level conveniences like explicit solver output retrieval or session list/close operations are absent, which is a minor gap.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers