model context protocol

AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists ACL 2026 DFAgent: From Natural Language Data Interactions to Reusable Agent-Ready Tools AAAI 2026 MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools AAAI 2026 MCPTox: A Benchmark for Tool Poisoning on Real-World MCP Servers AAAI 2026 MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration ACL 2026 MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments ACL 2026 MPMA: Preference Manipulation Attack Against Model Context Protocol AAAI 2026 SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning ACL 2026 Securing the Tool Layer: A Threat Taxonomy and Runtime Defense Framework for Model Context Protocol Deployments ACL 2026 SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP Agents ACL 2026 TPS-Bench: Evaluating AI Agents’ Tool Planning & Scheduling Abilities in Compounding Tasks ACL 2026 AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis EMNLP 2025 Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models EMNLP 2025 LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System EMNLP 2025 MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol EMNLP 2025 MCP2OSC: Parametric Control by Natural Language NeurIPS 2025 MCP-Driven Parametric Modeling: Integrating LLM Agents into Architectural and Landscape Design Workflows NeurIPS 2025 MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models EMNLP 2025 Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents EMNLP 2025 Tool Preferences in Agentic LLMs are Unreliable EMNLP 2025