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.

翻译：基于大型语言模型（LLM）驱动的智能体化工作流正日益应用于建筑信息模型（BIM）领域，实现了对IFC模型进行自然语言检索、修改与生成。近期研究开始采用新兴的模型上下文协议（MCP）作为LLM的统一工具调用接口，从而简化了BIM交互中智能体端的复杂性。尽管MCP标准化了LLM调用工具的方式，但当前BIM端的实现仍局限于特定工具且具有临时性，这限制了跨环境的复用性、评估能力及工作流可移植性。本文针对这一不足，提出了一种用于MCP服务器的模块化参考架构，该架构支持与具体API无关、隔离且可复现的智能体化BIM交互。通过对近期文献中反复出现的能力进行系统分析，我们提炼出一组核心需求。基于这些需求，我们设计了一种以显式适配器合约为中心的微服务架构，该合约将MCP接口与具体的BIM-API解耦。利用IfcOpenShell实现的原型系统验证了该架构在常见修改与生成任务中的可行性。在典型场景下的评估表明，该架构能够支持可靠的工作流、降低耦合度，并为系统性研究提供了可复用的基础。