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.
@article{arxiv.2601.00809,
title = {A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction},
author = {Tobias Heimig-Elschner and Changyu Du and Anna Scheuvens and André Borrmann and Jakob Beetz},
journal= {arXiv preprint arXiv:2601.00809},
year = {2026}
}
Comments
Accepted at the GNI Symposium on Artificial Intelligence for the Built World (Technical University of Munich, May 18--20, 2026)