AI RESEARCH
Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation
arXiv CS.AI
•
ArXi:2512.06556v2 Announce Type: replace-cross The Model Context Protocol (MCP) enables Large Language Models (LLMs) to interact with external tools via tool descriptors, thereby extending their capabilities for task execution, autonomous decision-making, and multi-agent coordination. Existing MCP deployments treat tool descriptors as trusted metadata, despite their direct integration into the LLM reasoning context. This