构建模块化MCP服务器架构，让大模型更稳定地操作建筑信息模型。
A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction
- 设计微服务架构，通过适配器解耦MCP接口与BIM API
- 在IfcOpenShell上验证，支持常见建模与生成任务
- 提升流程可复用性，适合研究大模型驱动的智能建造
基于大语言模型（LLMs）的智能体工作流正被广泛应用于建筑信息模型（BIM），实现自然语言对IFC模型的检索、修改与生成。近期研究开始采用新兴的模型上下文协议（MCP）作为统一工具调用接口，简化了大模型侧的交互。然而，当前BIM端的实现仍依赖特定工具、临时编写，限制了复用性、评估与跨环境工作流迁移。本文提出一种模块化参考架构，用于MCP服务器，实现API无关、隔离且可复现的智能体式BIM交互。通过对近年文献中常见能力的系统分析，提炼出核心需求，并构建以显式适配器契约为中心的微服务架构，将MCP接口与具体BIM-API解耦。原型基于IfcOpenShell实现，验证了在典型修改与生成任务中的可行性。在代表性场景下的评估表明，该架构能保障工作流可靠性，降低耦合度，为系统性研究提供可复用基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。