New MCP proxy enforces LLM tool access control architecturally

Researchers have developed a new architectural enforcement method called the MCP proxy to control Large Language Model (LLM) access to tools. This proxy addresses a critical security gap where LLMs can select unauthorized tools even when explicitly instructed not to. By removing unauthorized tools from the model's context during discovery and adding a second check at invocation, the MCP proxy effectively eliminates unauthorized tool usage across multiple LLM models and adversarial scenarios. The study demonstrates that architectural enforcement, rather than prompt-based restrictions, is essential for secure tool access control in deployed agentic systems. AI

影响 This research introduces a robust architectural solution for LLM tool access control, crucial for the safe deployment of agentic AI systems.

排序理由 The cluster contains an academic paper detailing a new method for LLM security. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Claude Haiku 3.5
• Large Language Models
• Llama 3.1 8B
• MCP proxy
• Qwen 2.5 7B

• 论文
• 安全
• 产品

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →