AI RESEARCH
Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search
arXiv CS.AI
•
ArXi:2603.24203v1 Announce Type: cross Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This creates a new class of powerful and tool augmented agents. Unfortunately, this capability also