MCP4IFC: IFC-Based Building Design Using Large Language Models

TL;DR

MCP4IFC is an open-source framework that enables large language models to directly manipulate IFC building data, facilitating AI-driven BIM design and editing through natural language instructions.

Contribution

The paper introduces MCP4IFC, a novel framework that integrates LLMs with IFC data manipulation using the Model Context Protocol, enabling complex building design tasks.

Findings

LLMs can successfully perform complex building design tasks using MCP4IFC.

The framework enables querying and editing existing IFC data effectively.

Open-source release promotes further research in AI-driven BIM workflows.

Abstract

Bringing generative AI into the architecture, engineering and construction (AEC) field requires systems that can translate natural language instructions into actions on standardized data models. We present MCP4IFC, a comprehensive open-source framework that enables Large Language Models (LLMs) to directly manipulate Industry Foundation Classes (IFC) data through the Model Context Protocol (MCP). The framework provides a set of BIM tools, including scene querying tools for information retrieval, predefined functions for creating and modifying common building elements, and a dynamic code-generation system that combines in-context learning with retrieval-augmented generation (RAG) to handle tasks beyond the predefined toolset. Experiments demonstrate that an LLM using our framework can successfully perform complex tasks, from building a simple house to querying and editing existing IFC data. Our framework is released as open-source to encourage research in LLM-driven BIM design and provide a foundation for AI-assisted modeling workflows. Our code is available at https://show2instruct.github.io/mcp4ifc/.