Search Results (9)

The construction industry faces challenges in estimating costs because the processes are time-consuming and involve a high likelihood of making errors. For instance, quantity take-offs are often inaccurate, and there is not a simple way to integrate data from Building Information Modeling (BIM) platforms and cost databases. This study introduces a framework that utilizes the Model Context Protocol (MCP) to ensure seamless integration between large language models (LLMs) and BIM models through Autodesk Revit in order to enable fully automated cost estimation workflows. The developed system combines an AI-powered MCP server with cost databases that are standard in the industry, such as the 2025 Craftsman National Building Cost Manual and the ZIP code-based location modifiers. This system enables LLMs to automatically obtain quantities from BIM models, match components to cost items, make regional changes, and make professional cost estimates. A case study of estimating the cost of an electrical system shows that the framework can reduce estimation time from 2.5–3.5 h (manual baseline) to 42.3 ± 3.7 s (n = 5 runs, warm start), representing a 98.6% efficiency gain, while being more accurate with respect to industry standards. The system processed 187 BIM elements in three component groups (receptacles, conduits, and panels). It automatically matched them to the right cost database items, used location-specific modifiers for ZIP code 01003, and made a full cost estimate of USD 13,945.81 with detailed breakdowns and a percent difference of %5.1 of the manual estimation. This research enhances automation in construction by developing a methodology for AI-BIM integration using standardized protocols, shows the practical application of AI in construction workflows, and provides empirical evidence of the advantages of automation in cost estimation processes. The results indicate that MCP-based AI integration presents a novel approach for construction automation, delivering improvements while applying professional standards of accuracy and availability. Full article

Large language models (LLMs) have rapidly transformed artificial intelligence applications across industries, yet their integration into production systems has unveiled critical security vulnerabilities, chief among them prompt injection attacks. This comprehensive review synthesizes research from 2023 to 2025, analyzing 45 key sources, industry security reports, and documented real-world exploits. We examine the taxonomy of prompt injection techniques, including direct jailbreaking and indirect injection through external content. The rise of AI agent systems and the Model Context Protocol (MCP) has dramatically expanded attack surfaces, introducing vulnerabilities such as tool poisoning and credential theft. We document critical incidents including GitHub Copilot’s CVE-2025-53773 remote code execution vulnerability (CVSS 9.6) and ChatGPT’s Windows license key exposure. Research demonstrates that just five carefully crafted documents can manipulate AI responses 90% of the time through Retrieval-Augmented Generation (RAG) poisoning. We propose PALADIN, a defense-in-depth framework implementing five protective layers. This review provides actionable mitigation strategies based on OWASP Top 10 for LLM Applications 2025, identifies fundamental limitations including the stochastic nature problem and alignment paradox, and proposes research directions for architecturally secure AI systems. Our analysis reveals that prompt injection represents a fundamental architectural vulnerability requiring defense-in-depth approaches rather than singular solutions. Full article

This paper presents a protocol-driven hybrid architecture that integrates Retrieval-Augmented Generation (RAG) with two complementary protocols—A Model Context Protocol (MCP) and an Agent Communication Protocol (ACP)—to deliver adaptive, transparent, and interoperable intelligent tutoring for higher-education STEM courses. MCP stores, fuses, and exposes session-, task- and course-level context (learning goals, prior errors, instructor flags, and policy constraints), while ACP standardizes multipart messaging and orchestration among specialized tutor agents (retrievers, context managers, pedagogical policy agents, execution tools, and generators). A Python prototype indexes curated course materials (two course corpora: a text-focused PDF and a multimodal PDF/transcript corpus) into a vector store and applies MCP-mediated re-ranking (linear fusion of semantic similarity, MCP relevance, instructor tags, and recency) before RAG prompt assembly. In a held-out evaluation (240 annotated QA pairs) and human studies (36 students, 12 instructors), MCP-aware re-ranking improved Recall@1, increased citation fidelity, reduced unsupported numerical claims, and raised human ratings for factuality and pedagogical appropriateness. Case studies demonstrate improved context continuity, scaffolded hinting under instructor policies, and useful multimodal grounding. The paper concludes that the ACP–MCP–RAG combination enables more trustworthy, auditable, and pedagogically aligned tutoring agents and outlines directions for multimodal extensions, learned re-rankers, and large-scale institutional deployment. Full article

Modern engineering increasingly operates within socio-technical networks, such as the interdependence of energy grids, transport systems, and building codes, where decisions must be reliable and transparent. Large language models (LLMs) such as GPT promise efficiency by interpreting domain-specific queries and generating outputs, yet their predictive nature can introduce biases or fabricated values—risks that are unacceptable in structural engineering, where safety and compliance are paramount. This work presents a dataset that embeds generative AI into validated computational workflows through the Model Context Protocol (MCP). MCP enables API-based integration between ChatGPT (GPT-4o) and numerical solvers by converting natural-language prompts into structured solver commands. This creates context-aware exchanges—for example, transforming a query on seismic drift limits into an OpenSees analysis—whose results are benchmarked against manually generated ETABS models. This architecture ensures traceability, reproducibility, and alignment with seismic design standards. The dataset contains prompts, GPT outputs, solver-based analyses, and comparative error metrics for four reinforced concrete frame models designed under Ecuadorian (NEC-15) and U.S. (ASCE 7-22) codes. The end-to-end runtime for these scenarios, including LLM prompting, MCP orchestration, and solver execution, ranged between 6 and 12 s, demonstrating feasibility for design and verification workflows. Beyond providing records, the dataset establishes a reproducible methodology for integrating LLMs into engineering practice, with three goals: enabling independent verification, fostering collaboration across AI and civil engineering, and setting benchmarks for responsible AI use in high-stakes domains. Full article

Ports and maritime operations generate massive real-time data streams, particularly from Automatic Identification System (AIS) signals, which are challenging to query effectively using natural language. This study proposes a prototype AISStream-MCP, a memory-augmented real-time maritime question-answering (QA) system that integrates live AIS data streaming with a Model Context Protocol (MCP) toolchain to support port operations decision-making. The system combines a large language model (LLM) with four MCP-enabled modules: persistent dialogue memory, live AIS data query, knowledge graph lookup, and result evaluation. We hypothesize that augmenting an LLM with domain-specific tools significantly improves QA performance compared to systems without memory or live data access. To test this hypothesis, we developed two prototype systems (with and without MCP framework) and evaluated them on 30 queries across three task categories: ETA prediction, anomaly detection, and multi-turn route queries. Experimental results demonstrate that AISStream-MCP achieves 88% answer accuracy (vs. 75% baseline), 85% multi-turn coherence (vs. 60%), and 38.7% faster response times (4.6 s vs. 7.5 s), with user satisfaction scores of 4.6/5 (vs. 3.5/5). The improvements are statistically significant (p < 0.01), confirming that memory augmentation and real-time tool integration effectively enhance maritime QA capabilities. Specifically, AISStream-MCP improved ETA prediction accuracy from 80% to 90%, anomaly detection from 70% to 85%, and multi-turn query accuracy from 65% to 88%. This approach shows significant potential for improving maritime situational awareness and operational efficiency. Full article

The integration of large language models (LLMs) into structural engineering workflows presents both a transformative opportunity and a critical challenge. While LLMs enable intuitive, natural language interactions with complex data, their limited arithmetic reasoning, contextual fragility, and lack of verifiability constrain their application in safety-critical domains. This study introduces a novel automation pipeline that couples generative AI with finite element modelling through the Model Context Protocol (MCP)—a modular, context-aware architecture that complements language interpretation with structural computation. By interfacing GPT-4 with OpenSeesPy via MCP (JSON schemas, API interfaces, communication standards), the system allows engineers to specify and evaluate 3D frame structures using conversational prompts, while ensuring computational fidelity and code compliance. Across four case studies, the GPT+MCP framework demonstrated predictive accuracy for key structural parameters, with deviations under 1.5% compared to reference solutions produced using conventional finite element analysis workflows. In contrast, unconstrained LLM use produces deviations exceeding 400%. The architecture supports reproducibility, traceability, and rapid analysis cycles (6–12 s), enabling real-time feedback for both design and education. This work establishes a reproducible framework for trustworthy AI-assisted analysis in engineering, offering a scalable foundation for future developments in optimisation and regulatory automation. Full article

Current learning and development approaches often struggle to capture dynamic individual capabilities, particularly the skills they acquire informally every day on the job. This dynamic creates a significant gap between what traditional models think people know and their actual performance, leading to an incomplete and often outdated understanding of how ready the workforce truly is, which can hinder organizational adaptability in rapidly evolving environments. This paper proposes a novel dynamic learner-state ecosystem—an AI-driven solution designed to bridge this gap. Our approach leverages specialized AI agents, orchestrated via the Model Context Protocol (MCP), to continuously track and evolve an individual’s multi-dimensional state (e.g., mastery, confidence, context, and decay). The seamless integration of in-workflow performance data will transform daily work activities into granular and actionable data points through AI-powered dynamic xAPI generation into Learning Record Stores (LRSs). This system enables continuous, authentic performance-based assessment, precise skill gap identification, and highly personalized interventions. The significance of this ecosystem lies in its ability to provide a real-time understanding of everyone’s capabilities, enabling more accurate workforce planning for the future and cultivating a workforce that is continuously learning and adapting. It ultimately helps to transform learning from a disconnected, occasional event into an integrated and responsive part of everyday work. Full article

Agentic AI systems, possessing capabilities for autonomous planning and action, show great potential across diverse domains. However, their practical deployment is hindered by challenges in aligning their behavior with varied human values, complex safety requirements, and specific compliance needs. Existing alignment methodologies often falter when faced with the complex task of providing personalized context without inducing confabulation or operational inefficiencies. This paper introduces a novel solution: a ‘superego’ agent, designed as a personalized oversight mechanism for agentic AI. This system dynamically steers AI planning by referencing user-selected ‘Creed Constitutions’—encapsulating diverse rule sets—with adjustable adherence levels to fit non-negotiable values. A real-time compliance enforcer validates plans against these constitutions and a universal ethical floor before execution. We present a functional system, including a demonstration interface with a prototypical constitution-sharing portal, and successful integration with third-party models via the Model Context Protocol (MCP). Comprehensive benchmark evaluations (HarmBench, AgentHarm) demonstrate that our Superego agent dramatically reduces harmful outputs—achieving up to a 98.3% harm score reduction and near-perfect refusal rates (e.g., 100% with Claude Sonnet 4 on AgentHarm’s harmful set) for leading LLMs like Gemini 2.5 Flash and GPT-4o. This approach substantially simplifies personalized AI alignment, rendering agentic systems more reliably attuned to individual and cultural contexts, while also enabling substantial safety improvements. Full article

Sulforaphane is considered the bioactive metabolite of glucoraphanin after dietary consumption of broccoli sprouts. Although both molecules pass through the gut lumen to the large intestine in stable form, their biological impact on the first intestinal tract is poorly described. In celiac patients, the function of the small intestine is affected by celiac disease (CD), whose severe outcomes are controlled by gluten-free dietary protocols. Nevertheless, pathological signs of inflammation and oxidative stress may persist. The aim of this study was to compare the biological activity of sulforaphane with its precursor glucoraphanin in a cellular model of gliadin-induced inflammation. Human intestinal epithelial cells (CaCo-2) were stimulated with a pro-inflammatory combination of cytokines (IFN-γ, IL-1β) and in-vitro-digested gliadin, while oxidative stress was induced by H₂O₂. LC-MS/MS analysis confirmed that sulforaphane from broccoli sprouts was stable after simulated gastrointestinal digestion. It inhibited the release of all chemokines selected as inflammatory read-outs, with a more potent effect against MCP-1 (IC₅₀ = 7.81 µM). On the contrary, glucoraphanin (50 µM) was inactive. The molecules were unable to counteract the oxidative damage to DNA (γ-H2AX) and catalase levels; however, the activity of NF-κB and Nrf-2 was modulated by both molecules. The impact on epithelial permeability (TEER) was also evaluated in a Transwell^® model. In the context of a pro-inflammatory combination including gliadin, TEER values were recovered by neither sulforaphane nor glucoraphanin. Conversely, in the context of co-culture with activated macrophages (THP-1), sulforaphane inhibited the release of MCP-1 (IC₅₀ = 20.60 µM) and IL-1β (IC₅₀ = 1.50 µM) only, but both molecules restored epithelial integrity at 50 µM. Our work suggests that glucoraphanin should not merely be considered as just an inert precursor at the small intestine level, thus suggesting a potential interest in the framework of CD. Its biological activity might imply, at least in part, molecular mechanisms different from sulforaphane. Full article