Tenable Research has identified a critical remote code execution vulnerability (CVE-2025-49596) in Anthropic’s widely adopted MCP Inspector, an open-source tool crucial for AI development. With a CVSS score of 9.4, this flaw leverages default, insecure configurations, leaving organisations exposed by design. MCP Inspector is a popular tool with over 38,000 weekly downloads on npmjs and more than 4,000 stars on GitHub.
Exploitation is alarmingly simple. A visit to a malicious website can fully compromise a workstation, requiring no further user interaction. Attackers can gain persistent access, steal sensitive data, including credentials and intellectual property, and enable lateral movement or deploy malware.
“Immediate action is non-negotiable”, says Rémy Marot, Staff Research Engineer at Tenable. “Security teams and developers should upgrade MCP Inspector to version 0.14.1 or later. This update enforces authentication, binds services to localhost, and restricts trusted origins, closing critical attack vectors. Prioritise robust security policies before deploying AI tools to mitigate these inherent risks.”