A critical remote code execution vulnerability has been discovered in Anthropic’s open‑source tool, MCP Inspector, which is widely used by AI developers for debugging Model Context Protocol (MCP) servers. Tracked as CVE-2025-49596, the vulnerability has a CVSS score of 9.4. Successful exploitation of the vulnerability may allow a remote unauthenticated attacker to execute arbitrary code … Continue reading “Anthropic Model Context Protocol (MCP) Inspector Remote Code Execution Vulnerability (CVE-2025-49596)”
