A high-severity authorization bypass in Google mcp-toolbox permits unauthenticated attackers to invoke tools via the HTTP API, posing a significant risk of unauthorized system operations.

The application fails to properly enforce authorization checks within the direct HTTP API tool invocation endpoint. This vulnerability is exploitable by unauthenticated attackers with network access to the service.

Successful exploitation allows unauthorized actors to execute arbitrary tools within the mcp-toolbox environment. Given the high CVSS score of 8.1, this flaw could lead to full compromise of the tool integration layer, resulting in unauthorized data access, manipulation, or service disruption.

Immediate Action: Update Google mcp-toolbox to the latest available version as provided by the vendor. Review the linked GitHub pull request for specific implementation details regarding the authorization fix.

Proactive Monitoring: Monitor API access logs for anomalous tool invocation patterns or requests originating from unknown or suspicious IP addresses.

Compensating Controls: Implement strict network access control lists (ACLs) to restrict access to the API endpoint to authorized internal segments only. Use a Web Application Firewall (WAF) to filter and block suspicious API requests.

Public Exploit Available: No

The vulnerability poses a severe risk to the integrity and availability of integrated systems. Organizations should prioritize patching this component immediately to prevent unauthorized tool execution.