IT之家 4 月 16 日消息，网络安全公司 OX Security 昨日（4 月 15 日）发布报告，披露 Anthropic 的 MCP（模型上下文协议）存在设计缺陷，可导致远程代码执行。该设计缺陷影响范围极广，导致超过 20 万台 AI ...

Ox安全研究团队表示，他们曾多次要求Anthropic从根本上修复这一问题，但均遭拒绝。Anthropic方面坚称该协议运行正常，尽管已有10个与MCP相关的开源工具和AI智能体获得了高危或严重级别的CVE编号。Ox认为，一次根本性的架构修复，原本可 ...

Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) architecture ...

智东西4月17日消息， 4月15日以色列网络安全公司OX ...

A design flaw – or expected behavior based on a bad design choice, depending on who is telling the story – baked into ...

However, in a report published on April 15, researchers at Ox Security claimed that a flaw in the protocol could enable ...

The AI company Anthropic, which was founded in 2021 by former OpenAI employees, has developed the Model Context Protocol (MCP) with the aim of standardizing communication between Large Language Models ...

Unsafe defaults in MCP configurations open servers to possible remote code execution, according to security researchers who ...

Microsoft's AI Toolkit extension for VS Code now includes a Tool Catalog that can scaffold a Python or TypeScript MCP server with the core transport and registration plumbing already set up. In ...