MCP4IFC: IFC-Based Building Design Using Large Language Models
This addresses the need for AI systems in architecture, engineering, and construction to translate natural language into actions on standardized data models, though it appears incremental as it builds on existing protocols and methods.
The paper tackles the problem of enabling Large Language Models to manipulate Industry Foundation Classes data for building design by introducing MCP4IFC, an open-source framework that allows LLMs to perform tasks like building a simple house and editing IFC data.
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/.