Skills Plugins MCP Prompt Model 博客 我的中心

mcp-servers-for-revit-integration

Connect AI assistants to Autodesk Revit via Model Context Protocol to read, create, modify, and delete Revit elements programmatically.

DeepseekModel 官方收录技能 质量 良好 · 64 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=aradotso-mcp-skills-skills-mcp-servers-for-revit-integration-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name mcp-servers-for-revit-integration description Connect AI assistants to Autodesk Revit via Model Context Protocol to read, create, modify, and delete Revit elements programmatically. triggers ["help me interact with Revit using MCP","set up mcp-servers-for-revit integration","create Revit elements through AI","query Revit model data","configure Revit MCP server","build custom Revit command set","connect Claude to Revit","automate Revit tasks with MCP"] mcp-servers-for-revit Integration Skill by ara.so — MCP Skills collection Overview mcp-servers-for-revit is a Model Context Protocol (MCP) implementation that enables AI assistants to interact with Autodesk Revit. It consists of three components: MCP Server (TypeScript) - Exposes tools to AI clients via stdio Revit Plugin (C#) - WebSocket bridge running inside Revit Command Set (C#) - Executes actual Revit API operations The system supports Revit 2020-2026 and provides 20+ tools for reading model data, creating elements, modifying properties, and exporting information. Installation Prerequisites Node.js 18+ Autodesk Revit 2020-2026 .NET Framework 4.8 (Revit 2020-2024) or .NET 8 (Revit 2025-2026) Quick Install (Release) Download the ZIP for your Revit version from Releases : mcp-servers-for-revit-v1.0.0-Revit2025.zip Extract to Revit addins folder: %AppData%\Autodesk\Revit\Addins\2025\ Configure MCP server in Claude Desktop ( claude_desktop_config.json ): { "mcpServers" : { "mcp-server-for-revit" : { "command" : "cmd" , "args" : [ "/c" , "npx" , "-y" , "mcp-server-for-revit" ] } } } For Claude Code (run in terminal): claude mcp add mcp-server-for-revit -- cmd /c npx -y mcp-server-for-revit Start Revit and click Always Load when prompted In Revit ribbon, click Settings on mcp-servers-for-revit tab, enable desired commands, and save Development Install Clone and build from source: git clone https://github.com/mcp-servers-for-revit/mcp-servers-for-revit.git cd mcp-servers-for-revit # Build MCP server cd server npm install npm run build # Build Revit plugin + command set # Open mcp-servers-for-revit.sln in Visual Studio # Select configuration: Release R25 (for Revit 2025) # Build solution Available Tools Data Extraction get_current_view_info // Returns info about active view { "name" : "get_current_view_info" , "arguments" : {} } get_current_view_elements // Get elements in current view { "name" : "get_current_view_elements" , "arguments" : { "category" : "Walls" // Optional: filter by category } } get_selected_elements // Get currently selected elements { "name" : "get_selected_elements" , "arguments" : {} } get_available_family_types // List available family types { "name" : "get_available_family_types" , "arguments" : { "category" : "Doors" // Required category } } get_material_quantities // Calculate material quantities { "name" : "get_material_quantities" , "arguments" : { "elementIds" : [ 123456 , 789012 ] } } analyze_model_statistics // Get model complexity metrics { "name" : "analyze_model_statistics" , "arguments" : {} } ai_element_filter // Intelligent element querying { "name" : "ai_element_filter" , "arguments" : { "query" : "all structural columns on level 2" } } Element Creation create_point_based_element // Create doors, windows, furniture { "name" : "create_point_based_element" , "arguments" : { "familyTypeId" : 654321 , "location" : { "x" : 10.0 , "y" : 20.0 , "z" : 0.0 }, "facingOrientation" : { "x" : 1.0 , "y" : 0.0 , "z" : 0.0 } } } create_line_based_element // Create walls, beams, pipes { "name" : "create_line_based_element" , "arguments" : { "familyTypeId" : 456789 , "startPoint" : { "x" : 0.0 , "y" : 0.0 , "z" : 0.0 }, "endPoint" : { "x" : 20.0 , "y" : 0.0 , "z" : 0.0 }, "levelId" : 123456 } } create_surface_based_element // Create floors, ceilings, roofs { "name" : "create_surface_based_element" , "arguments" : { "familyTypeId" : 987654 , "boundary" : [ { "x" : 0.0 , "y" : 0.0 }, { "x" : 20.0 , "y" : 0.0 }, { "x" : 20.0 , "y" : 15.0 }, { "x" : 0.0 , "y" : 15.0 } ], "levelId" : 123456 } } create_grid // Create grid system { "name" : "create_grid" , "arguments" : { "direction" : "vertical" , "count" : 5 , "spacing" : 20.0 , "startPoint" : { "x" : 0.0 , "y" : 0.0 , "z" : 0.0 }, "length" : 50.0 } } create_level // Create levels { "name" : "create_level" , "arguments" : { "elevation" : 14.0 , "name" : "Level 2" } } create_room // Place rooms { "name" : "create_room" , "arguments" : { "levelId" : 123456 , "location" : { "x" : 10.0 , "y" : 10.0 }, "name" : "Conference Room" , "number" : "201" } } create_dimensions // Create dimension annotations { "name" : "create_dimensions" , "arguments" : { "elementIds" : [ 123456 , 789012 ], "viewId" : 345678 } } create_structural_framing_system // Create beam framing { "name" : "create_structural_framing_system" , "arguments" : { "beamTypeId" : 456789 , "boundary" : [ { "x" : 0.0 , "y" : 0.0 }, { "x" : 40.0 , "y" : 0.0 }, { "x" : 40.0 , "y" : 30.0 }, { "x" : 0.0 , "y" : 30.0 } ], "spacing" : 10.0 , "levelId" : 123456 } } Element Modification delete_element // Delete elements { "name" : "delete_element" , "arguments" : { "elementIds" : [ 123456 , 789012 ] } } operate_element // Perform operations (select, hide, setColor) { "name" : "operate_element" , "arguments" : { "operation" : "setColor" , "elementIds" : [ 123456 ], "color" : { "red" : 255 , "green" : 0 , "blue" : 0 } } } color_elements // Color by parameter value { "name" : "color_elements" , "arguments" : { "parameterName" : "Fire Rating" , "colorScheme" : { "1 Hour" : { "red" : 255 , "green" : 255 , "blue" : 0 }, "2 Hour" : { "red" : 255 , "green" : 0 , "blue" : 0 } } } } Annotation tag_all_walls // Tag all walls in view { "name" : "tag_all_walls" , "arguments" : { "viewId" : 345678 } } tag_all_rooms // Tag all rooms in view { "name" : "tag_all_rooms" , "arguments" : { "viewId" : 345678 } } Data Export export_room_data // Export room information to CSV { "name" : "export_room_data" , "arguments" : { "outputPath" : "C:\\exports\\rooms.csv" } } store_project_data // Store project metadata to local DB { "name" : "store_project_data" , "arguments" : { "metadata" : { "projectName" : "Office Building" , "client" : "Acme Corp" } } } store_room_data // Store room metadata to local DB { "name" : "store_room_data" , "arguments" : { "roomId" : 123456 , "metadata" : { "department" : "Engineering" , "capacity" : 12 } } } query_stored_data // Query stored data { "name" : "query_stored_data" , "arguments" : { "query" : "SELECT * FROM rooms WHERE department = 'Engineering'" } } Advanced send_code_to_revit // Execute C# code in Revit context { "name" : "send_code_to_revit" , "arguments" : { "code" : "var doc = Application.ActiveUIDocument.Document; return new FilteredElementCollector(doc).OfClass(typeof(Wall)).GetElementCount();" } } Command Set Development Creating Custom Commands Commands inherit from RevitMCPCommandSet.BaseCommand : using Autodesk.Revit.DB; using Autodesk.Revit.UI; using RevitMCPCommandSet; using System.Collections.Generic; public class CreateCustomElement : BaseCommand { public override string Name => "create_custom_element" ; public override string Description => "Creates a custom element" ; public override Dictionary< string , object > Execute ( UIApplication uiApp, Dictionary< string , object > parameters ) {
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。