Conceptualising RAG-Driven Agentic AI with Multi-Layer MCP for Seismic Structural Systems

The integration of Generative AI into civil engineering is currently constrained by the risk of non-compliant outputs and an inherent lack of physics-based knowledge. To address these limitations, this paper presents a conceptual framework for the integration of Agentic Artificial Intelligence (AI) into the complete lifecycle of seismic-resistant structural engineering. The proposal employs a modular software architecture built on the Model Context Protocol (MCP), enabling distributed collaboration among specialised AI agents. We operationalise this architecture across six critical stages, where specific agents govern distinct phases: (1) Seismic Hazard and (2) Structural Modelling agents quantify demands through deterministic tool execution; the (3) Design agent optimises element sizing under the strict governance of Retrieval-Augmented Generation (RAG) for code compliance; (4) Construction Quality Control and (5) Structural Health Monitoring (SHM) agents validate as-built geometry and service-life performance; and an overarching (6) Ethical Audit agent supervises the ecosystem to ensure safety and algorithmic transparency. By decoupling probabilistic design iteration from immutable numerical execution, this framework ensures that generative outputs are traceable, transparent, and professionally accountable, offering a verified pathway for the deployment of AI systems in structural engineering.