About RevitMCPServer
RevitMCPServer connects AI assistants to Autodesk Revit through MCP for users who need to inspect or automate building models. Its tools cover element management as well as creating model components and views.
Key features
- 01Discover and execute Revit commands
- 02Read views and selected elements
- 03Find elements and edit parameters
- 04Move, delete, or highlight elements
- 05Create building and MEP components
- 06Create sheets and link DWG files
Use cases
- 01Find and inspect model elements by category
- 02Update element parameters or positions
- 03Create levels, walls, and doors
- 04Generate views, rooms, or sheets
MCP support
As an MCP server, it exposes Revit commands and model-operation tools to MCP clients. AI assistants can use it to discover and control the Revit plugin.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMExml.Revit.MCP Tools Overview
xml.Revit.MCP provides a comprehensive set of tools for integrating with Autodesk Revit through the Model Context Protocol (MCP). This library serves as a bridge between AI assistants and Revit, enabling powerful automation capabilities and programmatic interaction with building models.

Key Features
The tool library includes numerous functions for Revit automation and interaction:
Basic Operations:
- Get available commands from Revit plugin
- Execute specified commands in Revit
- Call specific Revit functions with parameters
- Retrieve view data and selected elements
Element Management:
- Find elements by category
- Get element parameters and locations
- Update element parameters
- Delete elements
- Show/highlight elements in current view
- Move elements to new positions
Creation Tools:
- Create levels/floors
- Create floor plan views
- Create grid lines
- Create walls and floors
- Create rooms and room tags
- Create doors and windows
- Create MEP elements (ducts, pipes, cable trays)
- Create family instances
- Link DWG files
- Create sheets
Installation Requirements
- xml.Revit: Version 1.3.4.3 or newer
- Python: 3.10 or newer
- UV Package Manager: Required for installation
- Revit: Compatible with versions 2019-2024 (with plugin)
Installation Process
-
First, install the UV package manager:
pip install uv -
Install the revit-mcp package:
pip install revit-mcp -
Test the installation:
uvx revit-mcpYou should see:
RevitMCPServer - INFO - Successfully connected to Revit on startup
Integration with AI Assistants
Claude for Desktop
Edit claude_desktop_config.json to include:
Cursor
Edit mcp.json to include:
Cline
Edit cline_mcp_setting.json to include:
{
"mcpServers": {
"RevitMCPServer": {
"disabled": false,
"timeout": 30,
"command": "uvx",
"args": ["revit-mcp"],
"transportType": "stdio",
"autoApprove": [
"active_view",
"call_func",
"create_cable_trays",
"create_door_windows",
"create_ducts",
"create_family_instances",
"create_floors",
"create_floor_plan_views",
"create_grids",
"create_levels",
"create_pipes",
"create_room_separation_lines",
"create_room_tags",
"create_rooms",
"create_sheets",
"create_walls",
"delete_elements",
"execute_commands",
"find_elements",
"get_commands",
"get_locations",
"get_selected_elements",
"get_view_data",
"link_dwg_and_activate_view",
"move_elements",
"parameter_elements",
"show_elements",
"update_elements"
]
}
}
}
Extending Functionality
You can create custom MCP DLL files to implement additional functionality by:
- Implementing the
xml.Revit.MCP.Public.IMCPMethodinterface - Following JSON-RPC 2.0 specification for communication
- Compiling to a DLL and placing it in the designated MCP folder
Plugin Configuration
When using the revit-mcp-plugin:
- Register the plugin with Revit
- Configure commands through: Add-in Modules → Revit MCP Plugin → Settings
- Enable the service: Add-in → Revit MCP Plugin → Revit MCP Switch
Once enabled, AI assistants can discover and control your Revit program, executing the various commands provided by the xml.Revit.MCP tools library.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.