mcp

Documents about mcp

• Orchestra: Corroboration-Based Regulatory Candidate Discovery via Composed Bioinformatics MCP Agents#1110338arXiv (OAI Expanded)
• HTN Planning as a Coordination Layer for Multi-Server MCP Tool Orchestration#1118804arXiv (All)
• MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security#2463arXiv CS
• CASCADE: A Cascaded Hybrid Defense Architecture for Prompt Injection Detection in MCP-Based Systems#120445arXiv CS
• Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives#120451arXiv CS
• Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models#128229arXiv CS
• Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control#200382arXiv CS
• Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications#259563arXiv CS
• Teaching Software Engineering with LLM and MCP Integration: From Classroom to Industry Practice#287190arXiv CS
• From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes#321774arXiv CS
• Governance Gaps in Agent Interoperability Protocols: What MCP, A2A, and ACP Cannot Express#324963arXiv CS
• Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog#394458arXiv CS
• Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation#451239arXiv CS
• ACLE-MCP: Attested Capability Leases for Execution-Time Trust in Remote LLM Tool Use#632765arXiv CS
• PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools#668480arXiv (OAI Expanded)
• PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools#670545arXiv (All)
• MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use#1011025arXiv (All)
• From Language to Action: Enhancing LLM Task Efficiency with Task-Aware MCP Server Recommendation#120604arXiv CS
• Influence of 1-methylcyclopropene (1-MCP) on 'Fuji' apple quality during long-term storage#210379Aperta
• When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool Calling#463168arXiv CS
• Can MCP Clients Decide What to Do After Failure? A Result-Only Actionability Audit#627769arXiv CS
• No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers#673429arXiv CS
• DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers#800109arXiv (All)
• PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs#965353arXiv CS
• Training-Free Refusal of MCP Exploits via Retrieval-Augmented Generation#1036698arXiv (All)
• MCP Error Messages Written for Developers Hurt the Most Capable Agents Most#1131693arXiv (All)
• CIViC MCP: Integrating Large Language Models with the Clinical Interpretations of Variants in Cancer#158248bioRxiv / medRxiv
• Parasites in the Toolchain: A Large-Scale Analysis of Attacks on the MCP Ecosystem#189340arXiv (OAI)
• Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control#682682arXiv (OAI Expanded)
• Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control#684457arXiv (All)
• ACLE-MCP: Attested Capability Leases for Execution-Time Trust in Remote LLM Tool Use#920596arXiv (OAI Expanded)
• ACLE-MCP: Attested Capability Leases for Execution-Time Trust in Remote LLM Tool Use#924830arXiv (All)
• MCP Error Messages Written for Developers Hurt the Most Capable Agents Most#1108817arXiv CS
• MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers#1131409arXiv (All)
• Uso de atmósfera controlada y 1-MCP en kiwis ´Hayward´ producidos en Argentina : efectos sobre la maduración = Controlled atmosphere storage and 1-MCP of ‘Hayward’ kiwifruits grown in Argentina : effects on ripening#307711DSpace
• mcp-proto-okn: Natural-language access to open scientific knowledge graphs through the Model Context Protocol#238650arXiv CS
• VFB-MCP: Natural-Language Access to Drosophila Neuroscience Grounded by an Expert-Curated Ontology-Led Knowledgebase#383460bioRxiv / medRxiv
• What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead#673584arXiv CS
• Test methods for CO2 mineralization in cement-based materials: A review by RILEM TC 309-MCP#677151HAL (France)
• Notch-mediated hepatocyte MCP-1 secretion causes liver fibrosis#677829IRIS
• A Safety-Bounded SDC-to-MCP Gateway for Medical AI Agents#1106057arXiv (All)
• From Legacy Documentation to OSCAL: An MCP-Based Agent Pipeline for Threat-Informed Continuous Compliance in Critical Infrastructure#352985arXiv CS
• SECOND EMERGENCY AND MALAYSIAN NATION-BUILDING#392300ScholarBank@NUS
• Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP#609051arXiv (OAI Expanded)
• An echocardiographic appreciation of rheumatic heart disease: phenotypic variability of valvular involvement and its prognostic implications.#975599NCBI PubMed Central
• What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead#998534arXiv (All)
• KGRAG: Knowledge Graph Orchestration & Retrieval Framework#157471Zenodo (CERN)
• A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem#444573arXiv CS
• Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study#632798arXiv CS
• No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers#1013684arXiv (All)