2 papers
cs.LG2025
MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment
John Halloran
The model context protocol (MCP) has been widely adapted as an open standard enabling the seamless integration of generative AI agents. However, recent work has shown the MCP is su…
cs.CR2025
MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
Brandon Radosevich, John Halloran
To reduce development overhead and enable seamless integration between potential components comprising any given generative AI application, the Model Context Protocol (MCP) (Anthro…