安全研究团队OX Security近日披露，由Anthropic公司开发并维护的AI通信协议标准MCP（Model Context Protocol）存在重大安全隐患。该协议的架构设计缺陷可能导致服务器遭受远程代码执行（RCE）攻击，威胁范围覆盖Python、Typescript、Java和Rust等所有支持语言，所有基于MCP构建的AI系统均面临潜在风险。 研究团队通过技术分析发现，漏洞源于协议 ...

团队建议，所有用户都不应该将大语言模型、AI 工具等暴露在公网环境，并且将 MCP 输入直接视为不可信数据，防止提示词注入。同时启用沙箱环境运行服务并时刻更新最新软件，将权限锁住。

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Dany Lepage discusses the architectural ...

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

Artificial intelligence has gone beyond being associated with highly complex algorithms or large amounts of data. Currently, the greatest complexity in artificial intelligence rests in the way answers ...

OpenAI Agents Now Support Rival Anthropic’s Protocol, Making Data Access ‘Simpler, More Reliable’ Your email has been sent Anthropic’s Model Context Protocol is effectively a universal language that ...

跨链协议 deBridge 宣布推出 Model Context Protocol（MCP），使 AI 代理及开发工具可在 EVM 链与 Solana 上执行非托管的跨链交换、桥接及多步骤链上操作。deBridge 表示，MCP 提供确定性执行与 MEV 感知路由，用户始终自持资产，并通过单一接口完成钱包编排、链切换与交易重试 ...

The Model Context Protocol (MCP) is redefining how artificial intelligence (AI) systems interact with external tools and services. By addressing the inherent limitations of large language models (LLMs ...

What if your AI assistant could not only answer your questions but also fetch real-time data, automate tedious tasks, and perform complex calculations, all seamlessly and without breaking stride?