PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-11624 Google CVE debrief

The Model Context Protocol has a security warning advising servers to validate the 'Origin' header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new '--allowed-hosts' flag was introduced alongside the existing '--allowed-origins' flag, enabling users to specify permitted hosts at server startup. Both flags default to '*', allowing users to implement strict access controls as needed without breaking existing setups. If either flag is set to '*', the server will output a startup warning about potential vulnerabilities. Documentation has also been updated to highlight these security considerations.

Vendor
Google
Product
MCP Toolbox for Databases
CVSS
CRITICAL 9.4
CISA KEV
Not listed in stored evidence
Original CVE published
2026-06-13
Original CVE updated
2026-06-13
Advisory published
2026-06-13
Advisory updated
2026-06-13

Who should care

Users of the Model Context Protocol, especially those who have not updated to version v0.25.0 or later, should be aware of this vulnerability and take necessary precautions to prevent DNS rebinding attacks.

Technical summary

The Model Context Protocol is vulnerable to DNS rebinding attacks due to a lack of validation of the 'Origin' header on incoming connections. This can be mitigated by using the '--allowed-hosts' and '--allowed-origins' flags to specify permitted hosts at server startup.

Defensive priority

High

Recommended defensive actions

  • Update to version v0.25.0 or later of the Model Context Protocol.
  • Use the '--allowed-hosts' and '--allowed-origins' flags to specify permitted hosts at server startup.
  • Implement strict access controls as needed.

Evidence notes

The CVE-2026-11624 record and NVD detail provide additional information about this vulnerability.

Official resources

CVE-2026-11624 was published on 2026-06-13T10:16:17.700Z and has a CVSS score of 9.4, indicating a critical vulnerability.