fluent-mcp-server

fluent-mcp-server

Provides smart URL navigation to ANSYS Fluent documentation, enabling AI assistants to quickly find relevant help pages and manual sections.

Category
访问服务器

README

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:

<details> <summary><b>Claude Code</b> (CLI)</summary>

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

Verify:

claude mcp list
claude mcp info fluent

</details>

<details> <summary><b>Claude Desktop</b></summary>

Add to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

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

Restart Claude Desktop completely after saving.

</details>

<details> <summary><b>Cursor</b></summary>

Go to Cursor Settings → MCP → Add new MCP Server:

  • Name: fluent
  • Command: uvx fluent-mcp-server

Or edit config file:

macOS: ~/Library/Application Support/Cursor/mcp_config.json Windows: %APPDATA%\Cursor\mcp_config.json Linux: ~/.config/Cursor/mcp_config.json

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

</details>

<details> <summary><b>VS Code</b> (GitHub Copilot)</summary>

CLI:

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

Or add to VS Code settings:

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

</details>

<details> <summary><b>Cline</b> (VS Code Extension)</summary>

Install Cline extension, then add to VS Code settings:

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

Reload VS Code window after saving.

</details>

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

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 md-files/ARCHITECTURE.md for detailed roadmap.

Documentation

Getting Started:

Technical Documentation:

Validation & Analysis:

Development:

License

MIT License

Contributing

Contributions welcome! Please ensure:

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

fluent-mcp-server

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选