Revit MCP
The Revit MCP server enables AI-driven interaction with Autodesk Revit through the MCP protocol, allowing you to:
Retrieve Data: Access information about the current view, selected elements, and available family types with filtering options
Element Management: Create, modify, and delete various elements:
Point-based (doors, windows, furniture)
Line-based (walls, beams, pipes)
Surface-based (floors, ceilings, roofs)
Model Enhancement: Color elements based on parameters, tag walls, and batch process elements for complex modeling tasks
Code Execution: Send and execute custom C# code directly in Revit
Reset Model: Delete process model when executing continuous dialog
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Revit MCPshow me all the walls in the current view"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🔴
Deprecation notice, this repo is being archived in favour of the mono repo approch for the mcphttps://github.com/mcp-servers-for-revit/mcp-servers-for-revit Simpler CI, less confusion for noobs, npm package and simpler install
revit-mcp
English | ç®€ä½“ä¸æ–‡
Description
revit-mcp allows you to interact with Revit using the MCP protocol through MCP-supported clients (such as Claude, Cline, etc.).
This project is the server side (providing Tools to AI), and you need to use revit-mcp-plugin (driving Revit) in conjunction.
Related MCP server: Revit MCP Server
Features
Allow AI to get data from the Revit project
Allow AI to drive Revit to create, modify, and delete elements
Send AI-generated code to Revit to execute (may not be successful, successful rate is higher in some simple scenarios with clear requirements)
Requirements
nodejs 18+
Complete installation environment still needs to consider the needs of revit-mcp-plugin, please refer to revit-mcp-plugin
Installation
1. Build local MCP service
Install dependencies
npm installBuild
npm run build2. Client configuration
Claude client
Claude client -> Settings > Developer > Edit Config > claude_desktop_config.json
{
"mcpServers": {
"revit-mcp": {
"command": "node",
"args": ["<path to the built file>\\build\\index.js"]
}
}
}Restart the Claude client. When you see the hammer icon, it means the connection to the MCP service is normal.

Framework
flowchart LR
ClaudeDesktop --> revit-mcp --> SocketService--commandName-->CommandSet--command-->CommandExecute
CommandManager --> CommandSet
CommandExecute --executeResult--> SocketService
CommandProject1 --> CommandManager
CommandProject2 --> CommandManager
CommandProject... --> CommandManager
subgraph ide1 [MCPClient]
ClaudeDesktop
end
subgraph ide2 [MCPServer]
revit-mcp
end
subgraph ide3 [Revit]
subgraph ide3.1 [revit-mcp-plugin]
SocketService
CommandSet
CommandManager
CommandExecute
end
endSupported Tools
Name | Description |
get_current_view_info | Get current active view info |
get_current_view_elements | Get elements from the current active view |
get_available_family_types | Get available family types in current project |
get_selected_elements | Get currently selected elements |
get_material_quantities | Calculate material quantities and takeoffs |
ai_element_filter | Intelligent element querying tool for AI assistants |
analyze_model_statistics | Analyze model complexity with element counts |
create_point_based_element | Create point-based elements (door, window, furniture) |
create_line_based_element | Create line-based elements (wall, beam, pipe) |
create_surface_based_element | Create surface-based elements (floor, ceiling, roof) |
create_grid | Create a grid system with smart spacing generation |
create_level | Create levels at specified elevations |
create_room | Create and place rooms at specified locations |
create_structural_framing_system | Create a structural beam framing system |
delete_element | Delete elements by ID |
operate_element | Operate on elements (select, setColor, hide, etc.) |
color_elements | Color elements based on a parameter value |
tag_all_walls | Tag all walls in the current view |
tag_all_rooms | Tag all rooms in the current view |
export_room_data | Export all room data from the project |
store_project_data | Store project metadata in local database |
store_room_data | Store room metadata in local database |
query_stored_data | Query stored project and room data |
send_code_to_revit | Send C# code to Revit to execute |
say_hello | Display a greeting dialog in Revit (connection test) |
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mcp-servers-for-revit/revit-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server