π€ AI Summary
This work addresses the limitations of existing Model Context Protocol (MCP)-based BIM interaction approaches, which are often tied to specific modeling tools and lack a unified architecture, resulting in poor reusability and limited cross-platform workflow portability. To overcome these challenges, the paper introduces the first modular MCP reference architecture tailored for BIM. By employing explicit adapter contracts, the architecture decouples MCP interfaces from concrete BIM APIs. Integrated with a microservices framework, the IFC standard, and the IfcOpenShell library, it enables API-agnostic, isolated, and reproducible agent interactions. A prototype implementation demonstrates the feasibility of this approach through representative modification and generation tasks, significantly reducing system coupling while enhancing workflow portability and research reproducibility.
π Abstract
Agentic workflows driven by large language models (LLMs) are increasingly applied to Building Information Modelling (BIM), enabling natural-language retrieval, modification and generation of IFC models. Recent work has begun adopting the emerging Model Context Protocol (MCP) as a uniform tool-calling interface for LLMs, simplifying the agent side of BIM interaction. While MCP standardises how LLMs invoke tools, current BIM-side implementations are still authoring tool-specific and ad hoc, limiting reuse, evaluation, and workflow portability across environments. This paper addresses this gap by introducing a modular reference architecture for MCP servers that enables API-agnostic, isolated and reproducible agentic BIM interactions. From a systematic analysis of recurring capabilities in recent literature, we derive a core set of requirements. These inform a microservice architecture centred on an explicit adapter contract that decouples the MCP interface from specific BIM-APIs. A prototype implementation using IfcOpenShell demonstrates feasibility across common modification and generation tasks. Evaluation across representative scenarios shows that the architecture enables reliable workflows, reduces coupling, and provides a reusable foundation for systematic research.