Revit MCP Server
An MCP server for integrating AI with Autodesk Revit, enabling seamless communication via WebSocket.
🏗️ Revit MCP Server
A Model Context Protocol server for Revit integration, enabling seamless communication between Claude AI and Autodesk Revit.
🎯 Overview
This TypeScript-based MCP server provides a bridge between Claude AI and Revit, allowing direct interaction with Revit models through a WebSocket connection. It implements the Model Context Protocol to enable:
- ⚡ Real-time access to Revit model information
- 🔍 Element querying and filtering
- 👀 View and level management
- 🛡️ Robust error handling with fallback mock data
✨ Features
🔌 Revit Integration
- 📡 WebSocket-based communication with Revit plugin
- 🔄 Real-time model data access
- 🔁 Graceful fallback to mock data when connection fails
- ⚙️ Configurable connection settings via environment variables
🚀 Core Functionalities
-
📊 Model Information
- Access basic model metadata (name, path, version)
- Get element counts and last modification date
- Real-time model state synchronization
-
🏗️ Element Management
- Query elements with flexible filtering
- Access element properties and geometry
- Batch element operations
-
🎪 View & Level Control
- List all available views
- Access level information
- Navigate through model hierarchy
💻 Development
📋 Prerequisites
- Node.js (v14 or higher)
- npm
- Autodesk Revit (2023 or later)
- Revit WebSocket Plugin (companion plugin)
🔧 Installation
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
⚙️ Configuration
The server can be configured using environment variables:
REVIT_HOST=127.0.0.1 # Revit plugin WebSocket host
REVIT_PORT=8080 # Revit plugin WebSocket port
🔗 Integration with Claude Desktop
Add the server configuration to Claude Desktop:
Windows:
%APPDATA%/Claude/claude_desktop_config.json
Configuration format:
{
"mcpServers": {
"revit-mcp-server": {
"command": "D:/path/to/revit-mcp-server/build/index.js"
}
}
}
🐛 Debugging
For debugging the MCP communication:
- Use the built-in MCP Inspector:
npm run inspector
- Monitor WebSocket communication with Revit plugin
- Check server logs for connection and operation status
⚠️ Error Handling
The server implements robust error handling:
- Automatic fallback to mock data when Revit connection fails
- Detailed error logging
- Graceful connection recovery
📄 License
MIT License
🤝 Contributing
Contributions are welcome! Please feel free to submit pull requests.
📬 Contact
If you have any questions or suggestions, feel free to reach out:
- 📧 Email: [email protected]
- 💬 WeChat Account: modian4500
関連サーバー
Scout Monitoring MCP
スポンサーPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
スポンサーAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Sleep MCP Server
Provides a sleep/wait tool to add delays between operations, such as waiting between API calls or testing eventually consistent systems.
AI Image Generation
Generate images using the Together AI API. Supports custom aspect ratios, save paths, and batch generation.
Linear Regression MCP
Train a Linear Regression model by uploading a CSV dataset file, demonstrating an end-to-end machine learning workflow.
ABP.IO MCP Server
An MCP server for ABP.IO that enables AI models to interact with your ABP applications and framework.
Auto API - YApi
A tool to retrieve API interface information from YApi, with authentication configurable via environment variables.
MCP_Agent:RE
Fetches requirements and defect data from the TAPD platform to provide data support for AI clients.
maximumsats-mcp
Bitcoin Lightning + Nostr Web-of-Trust tools for agents (L402 pay-per-call endpoints)
Persona MCP Server
Dynamically manage AI personas from markdown files for AI assistants like Claude.
MCP Server Automation CLI
A command-line tool to automate the deployment of MCP servers to AWS ECS.
MCP Gateway
A reverse proxy gateway for managing and accessing multiple MCP servers through a single entry point, deployable via Docker.