This paper has been withdrawn by Yuhang Huang

[Submitted on 8 Mar 2026 (v1), last revised 21 Jul 2026 (this version, v2)]

No PDF available, click to view other formats

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. However, the security of MCP-based systems remains largely this http URL this work, we conduct a large-scale security analysis of MCP servers integrated within MCP clients. We show that treating MCP servers as trusted entities without authenticating the caller identity is fundamentally insecure. Since MCP servers often cannot distinguish who is invoking a request, a single authorization decision may implicitly grant access to multiple, potentially untrusted this http URL empirical study reveals that most MCP servers rely on persistent authorization states, allowing tool invocations after an initial authorization without re-authentication, regardless of the caller. In addition, many MCP servers fail to enforce authentication at the per-tool level, enabling unauthorized access to sensitive this http URL findings demonstrate that one-time authorization and server-level trust significantly expand the attack surface of MCP-based systems, highlighting the need for explicit caller authentication and fine-grained authorization mechanisms.

Submission history

From: Yuhang Huang [view email]
[v1] Sun, 8 Mar 2026 05:24:16 UTC (943 KB)
[v2] Tue, 21 Jul 2026 07:52:02 UTC (1 KB) (withdrawn)