Critical Vulnerability Discovered in Anthropic's Model Context Protocol (MCP) Inspector
CybersecurityVulnerabilityArtificialIntelligenceRemoteCodeExecutionAnthropicMCPInspectorCVE-2025-49596CVSSDevelopersRemoteExploits
Cybersecurity researchers have discovered a critical vulnerability in the Model Context Protocol (MCP) Inspector project of the artificial intelligence company Anthropic. This flaw, listed under the number CVE-2025-49596, has a CVSS score of 9.4 out of 10.0 and could allow remote code execution (RCE), giving an attacker full access to hosts. The vulnerability affects developers' machines, exposing these systems to remote exploits.