mcp-servers-for-revit  by mcp-servers-for-revit

Connect AI assistants to Autodesk Revit

Created 6 months ago
254 stars

Top 99.1% on SourcePulse

GitHubView on GitHub
Project Summary

This project provides a robust bridge between AI assistants and Autodesk Revit, enabling sophisticated automation and data manipulation within BIM projects. It targets engineers, researchers, and power users who need to programmatically interact with Revit models using AI tools like Claude and Cline, offering significant benefits in design exploration, analysis, and documentation workflows.

How It Works

The architecture comprises three core components: a Node.js-based MCP Server that translates AI client requests into a standardized protocol, a C# Revit Add-in (Plugin) that acts as a WebSocket bridge within Revit, and a C# Command Set that executes the actual Revit API operations. AI clients communicate with the MCP Server via stdio, which then relays commands over WebSockets to the Revit Plugin. The plugin dispatches these commands to the Command Set, which interfaces directly with the Revit API to perform read, create, modify, or delete operations, returning results back up the chain.

Quick Start & Requirements

  • Primary Install/Run: Download a release ZIP for your Revit version from the Releases page, extract to your Revit Addins folder (%AppData%\Autodesk\Revit\Addins\<your Revit version>\), and configure your AI client to run the MCP server (e.g., npx -y mcp-server-for-revit).
  • Prerequisites: Node.js 18+ (for MCP server), Autodesk Revit 2020-2026.
  • Links: Releases page (implied), MCP Server Setup documentation (for AI client integration).

Highlighted Details

  • Extensive Toolset: Supports a wide array of operations including querying view/element data, family types, selected elements, material quantities, intelligent element filtering, model statistics analysis, creating various element types (point-based, line-based, surface-based), generating grids/levels, placing rooms, creating annotations, structural framing, deleting elements, operating on elements (color, hide), tagging, exporting room data, storing/querying project data, and executing arbitrary C# code within Revit.
  • Forked Functionality: This project is a fork of the original revit-mcp, incorporating additional tools and functional improvements.
  • Integrated Testing: Features an integration testing framework using Nice3point.TUnit.Revit that runs tests against a live Revit instance, requiring a licensed installation.

Maintenance & Community

The project includes CI/CD workflows in .github/ and an automated release process triggered by Git tags. Specific community links (Discord/Slack) or details on maintainers/sponsorships are not explicitly provided in the README.

Licensing & Compatibility

  • License: MIT. This permissive license allows for commercial use and integration into closed-source projects.
  • Compatibility: Supports Autodesk Revit versions 2020 through 2026. Development targets .NET Framework 4.8 for Revit 2020-2024 and .NET 8 for Revit 2025-2026.

Limitations & Caveats

Setup requires managing both a Node.js environment for the MCP server and the Revit add-in installation. Testing necessitates a licensed Revit installation and specific SDKs (.NET 10 SDK). As a fork, users should be aware of potential divergences from the original revit-mcp project.

Health Check
Last Commit

4 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
0 stars in the last 30 days

Explore Similar Projects

Starred by Eric Zhu Eric Zhu(Coauthor of AutoGen; Research Scientist at Microsoft Research), Elie Bursztein Elie Bursztein(Cybersecurity Lead at Google DeepMind), and
27 more.

goose by aaif-goose

0%
51k
Open-source AI agent for automating complex engineering tasks
Created 2 years ago
Updated 20 hours ago
Feedback? Help us improve.