mcpField
R

Revit Mcp

Local
github.com/revit-mcpMedia & Design475Updated 35w ago

About Revit Mcp

Revit Mcp is an MCP server that lets MCP-supported clients interact with Revit projects, in conjunction with revit-mcp-plugin. It exposes tools for model inspection and element editing, as well as sending C# code to Revit; the repository is marked for archival in favor of a mono-repo.

Key features

  1. 01Read active-view and selection data
  2. 02Inspect families, quantities, and model statistics
  3. 03Create and modify Revit elements
  4. 04Tag walls and rooms and export room data
  5. 05Send C# code to Revit

Use cases

  1. 01Querying the current Revit view from an AI client
  2. 02Creating or removing model elements through tools
  3. 03Calculating material quantities and reviewing model statistics
  4. 04Exporting room data or running C# code in Revit

MCP support

The server exposes Revit project data and operations as tools to MCP clients. It must be used together with revit-mcp-plugin, which drives Revit.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🔴

Warning

Deprecation notice, this repo is being archived in favour of the mono repo approch for the mcp https://github.com/mcp-servers-for-revit/mcp-servers-for-revit Simpler CI, less confusion for noobs, npm package and simpler install



MseeP.ai Security Assessment Badge

revit-mcp

English | 简体中文

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.

Join Discord | QQ Group

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 install

Build

npm run build
2. 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.

claude

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
	end

Supported Tools

NameDescription
get_current_view_infoGet current active view info
get_current_view_elementsGet elements from the current active view
get_available_family_typesGet available family types in current project
get_selected_elementsGet currently selected elements
get_material_quantitiesCalculate material quantities and takeoffs
ai_element_filterIntelligent element querying tool for AI assistants
analyze_model_statisticsAnalyze model complexity with element counts
create_point_based_elementCreate point-based elements (door, window, furniture)
create_line_based_elementCreate line-based elements (wall, beam, pipe)
create_surface_based_elementCreate surface-based elements (floor, ceiling, roof)
create_gridCreate a grid system with smart spacing generation
create_levelCreate levels at specified elevations
create_roomCreate and place rooms at specified locations
create_structural_framing_systemCreate a structural beam framing system
delete_elementDelete elements by ID
operate_elementOperate on elements (select, setColor, hide, etc.)
color_elementsColor elements based on a parameter value
tag_all_wallsTag all walls in the current view
tag_all_roomsTag all rooms in the current view
export_room_dataExport all room data from the project
store_project_dataStore project metadata in local database
store_room_dataStore room metadata in local database
query_stored_dataQuery stored project and room data
send_code_to_revitSend C# code to Revit to execute
say_helloDisplay a greeting dialog in Revit (connection test)

Comments

Markdown supported

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.