subspace-lab/fluent-mcp-server

ANSYS Fluent MCP Server

A Model Context Protocol (MCP) server that helps AI assistants navigate ANSYS Fluent online documentation efficiently.

Features

• Smart URL Navigator - Find relevant ANSYS Help documentation URLs instantly
• 35+ Topic Routes - Pre-mapped paths to common Fluent topics
• Always Up-to-Date - Points to official ANSYS documentation
• Zero Maintenance - No static content to update
• Lightweight - Fast URL generation, no heavy indexing

Quick Start

Prerequisites

• Python 3.10 or higher
• uv package manager

Installation

Choose your MCP client below for setup instructions:

claude mcp add fluent -- uvx fluent-mcp-server

claude mcp list
claude mcp info fluent

{
  "mcpServers": {
    "fluent": {
      "command": "uvx",
      "args": ["fluent-mcp-server"]
    }
  }
}

{
  "mcpServers": {
    "fluent": {
      "command": "uvx",
      "args": ["fluent-mcp-server"]
    }
  }
}

code --add-mcp '{"name":"fluent","command":"uvx","args":["fluent-mcp-server"]}'

{
  "github.copilot.chat.mcp.servers": {
    "fluent": {
      "command": "uvx",
      "args": ["fluent-mcp-server"]
    }
  }
}

{
  "cline.mcpServers": {
    "fluent": {
      "command": "uvx",
      "args": ["fluent-mcp-server"]
    }
  }
}

For 11 additional clients (Windsurf, Continue, Amp, Codex, Gemini CLI, Goose, Kiro, LM Studio, opencode, Qodo Gen, Warp), see

Local Development

# Clone the repository
git clone https://github.com/your-org/fluent-mcp-server.git
cd fluent-mcp-server

# Install with uv
uv pip install -e ".[dev]"

# Run tests
uv run pytest

# Run server
uv run fluent-mcp-server

Development configuration (.mcp.json in project root):

{
  "mcpServers": {
    "fluent": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/fluent-mcp-server",
        "run",
        "fluent-mcp-server"
      ]
    }
  }
}

Available Tools

search_help

Find ANSYS Fluent documentation URLs for your query. Returns search URLs and suggested manual sections.

Parameters:

• query (required): Search term (e.g., "flamelet model", "read case", "turbulence")
• max_suggestions (optional): Maximum manual section suggestions (default: 3)

Returns:

• ANSYS Help search URL
• Suggested manual sections (if topic is pre-mapped)
• Links to all major manuals

Example:

search_help("flamelet model")
# Returns:
# - Search URL: https://ansyshelp.ansys.com/search?q=flamelet+model
# - Suggested: flamelet User Guide + Theory Guide
# - All manuals: User Guide, TUI, Theory, UDF

search_help("read case")
# Returns URLs to file/read-case TUI documentation

list_topics

List the 35+ topics with pre-mapped documentation routes.

Returns: List of topics like: file, turbulence, combustion, flamelet, mesh, boundary, udf, etc.

Example:

list_topics()

get_manual_link

Get direct link to a specific Fluent manual or section.

Parameters:

• manual (required): Manual name (user_guide, tui, theory, udf)
• section (optional): Section path (e.g., "turbulence", "file/read-case")

Example:

get_manual_link("udf", "introduction")
# Returns: https://ansyshelp.ansys.com/.../flu_udf/introduction.html

Usage Examples

In Claude Code / AI Assistant

You: How do I use the flamelet model in Fluent?
Claude: [Calls search_help("flamelet model")]
        [Receives URLs to flamelet documentation]
        [Uses WebFetch to read the actual documentation]
        [Provides answer based on official ANSYS docs]

You: Show me the command to read a case file
Claude: [Calls search_help("read case")]
        [Gets URL to file/read-case TUI command]
        [Retrieves documentation and shows syntax]

Architecture Flow

User Query → MCP search_help → Returns URLs →
LLM uses WebFetch → Reads official docs → Answers user

The MCP server acts as a smart navigator, not a content database.

Architecture

fluent-mcp-server/
├── src/fluent_mcp_server/
│   ├── server.py          # FastMCP server & tool definitions
│   ├── doc_finder.py      # Smart URL router (35+ topic mappings)
│   └── __init__.py
├── md-files/
│   ├── ARCHITECTURE.md    # Technical architecture
│   └── ...
├── tests/                 # Unit tests
├── examples/              # Usage examples
└── pyproject.toml        # Project configuration

Roadmap

Phase 1.x: Route Expansion (Future)

• Add more topic routes based on usage patterns
• Version selection (v251, v252, v253)
• Usage analytics to identify popular topics

Phase 2: PyFluent Integration (Planned)

• Connect to Fluent sessions
• Execute TUI commands programmatically
• Case I/O via PyFluent API
• Mesh quality automation
• Convergence monitoring

Phase 3: Workflow Automation (Planned)

• Boundary condition templates
• Solver configuration wizards
• Post-processing automation
• Parametric studies

See for detailed roadmap.

Documentation

Getting Started:

• - Setup and usage guide
• - This file (overview)

Technical Documentation:

• - System architecture and design
• - Complete tool catalog
• - ANSYS Help site patterns

Validation & Analysis:

• - Real user questions
• - Coverage analysis
• - User scenarios

Development:

• - Usage examples
• - Unit tests

License

MIT License

Contributing

Contributions welcome! Please ensure:

• Tests pass: uv run pytest
• Code follows existing style
• Documentation updated

fluent-mcp-server