PyNet Bridge
PyNet Bridge MCP implementation to connect IAs with PyNet Platform.
README
🐍 PyNet Platform Bridge (MCP)
PyNet Platform Bridge is a Model Context Protocol (MCP) server that enables AI models (such as Claude, GPT-4o, or Gemini) to interact directly with Autodesk Tools through the PyNet Platform.
This bridge acts as the connective tissue between AI logic and Autodesk desktop APIs, allowing for dynamic UI creation, script execution, and BIM process automation using natural language.
🚀 Key Features
- Dynamic UI Deployment: Allows the AI to create custom Ribbon tabs (modules) and buttons in Navisworks/Revit in real-time.
- Script Execution: Seamlessly send and execute Python code directly within the PyNet Platform's internal engine.
- Instance Detection: Automatically locates active Navisworks/Revit processes using PID tracking via psutil.
- Robust Communication: Built on Named Pipes for low-latency, high-reliability IPC (Inter-Process Communication).
- Open Ecosystem: Compatible with any MCP client (Claude Desktop, Cursor, VS Code, Zed, etc.).
🛠️ Installation
1. Prerequisites
- PyNet Platform plugin installed in Navisworks/Revit.
- Python 3.10 or higher.
2. Install the Bridge
Run the following command in your terminal:
pip install .
This will register the pynet-bridge command globally in your system.
⚙️ Configuration for Claude Desktop
To allow Claude to control your BIM environment, add the server to your Claude Desktop configuration file.
File Path: %APPDATA%\Claude\claude_desktop_config.json
Configuration JSON:
{
"mcpServers": {
"pynet-platform": {
"command": "pynet-bridge",
"args": []
}
}
}
🛠️ Available MCP Tools
Once connected, the AI will have access to the full suite of PyNet tools:
🔍 System & Connection
- list_active_instances: Scans the system for running Navisworks processes (
roamer.exe) with an active PyNet IPC pipe. - check_plugin_status: Handshake ping to verify the plugin listener is responsive.
🏗️ Module (Tab) Management
- get_pynet_ui_layout: Fetches the full UI structure (ButtonsModules and ScriptButtons).
- create_pynet_module: Creates a new custom Tab (ButtonsModule) in the Ribbon.
- delete_pynet_module: Permanently deletes a module and all its contents.
🔘 Button Management
- get_buttons_data: Lists all script buttons for a specific module ID.
- deploy_script_button: Installs a new ScriptButton into a specific module (Name, Script, Icon, Tooltip).
- update_script_button: Updates metadata for an existing ScriptButton or moves it to another module.
- delete_script_button: Permanently removes a ScriptButton from a module by Id.
💻 Execution & Console Control
- send_command: Direct script execution in the PyNet engine (Target PID, Script Name, Content).
- get_output_window_status: Checks if the output window is currently available/visible.
- configure_output_window: Toggles the visibility of the PyNet log/output window.
📂 Project Structure
- pynet_mcp/: Core MCP server logic (FastMCP).
- pyproject.toml: Package configuration and dependency management.
📄 License
This project is licensed under the MIT License.
Built with ❤️ for the BIM Community by rafa2403nunez
<p align="center"> <img src="https://raw.githubusercontent.com/rafa2403nunez-droid/PyNetBridge/develop/Assets/RAEN%20Digital%20Tools.png" alt="RAEN Digital Tools" width="200"> </p>
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。