arXiv AI By Yuhang Huang, Boyang Ma, Biwei Yan, Xuelong Dai, Yechao Zhang, Minghui Xu, Kaidi Xu, Yue Zhang

Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems

Read the original on arXiv AI →

arXiv:2603. 07473v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 2

Attested Tool-Server Admission: A Security Extension to the Model Context Protocol

arXiv:2605. 24248v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which servers it may use, at what sensitivity, or which of a server's tools are in bounds.

By Alfredo Metere