Anthropic MCP Design Vulnerability Enables RCE, Threatening AI Supply Chain
Cybersecurity researchers discovered a critical vulnerability in Anthropic's Model Context Protocol, enabling remote code execution and threatening the AI supply chain. The flaw affects over 7,000 publicly accessible servers and software packages with over 150 million downloads.
Cybersecurity researchers have found a critical 'by design' weakness in Anthropic's Model Context Protocol (MCP) that enables remote code execution and threatens the AI supply chain. The vulnerability affects MCP implementations across multiple programming languages, including Python, TypeScript, Java, and Rust. It impacts over 7,000 publicly accessible servers and software packages with over 150 million downloads. The flaw arises from unsafe defaults in MCP configuration over the STDIO transport interface, resulting in 10 identified vulnerabilities. Anthropic has declined to modify the protocol's architecture, citing the behavior as 'expected.' To mitigate the threat, experts advise blocking public IP access to sensitive services, monitoring MCP tool invocations, and running MCP-enabled services in a sandbox.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.