← Security Alerts

CVE-2026-11624

Google LLC · published 2026-06-13

Source record Collected from the National Vulnerability Database (NVD)

Description

Description by Google Inc. via the CVE Program.

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.

Status at the source

Affected products, as the source lists them

VendorProductVersions
GoogleMCP Toolbox for Databases0 – before 0.25.0: affected

DeSpy has not checked any unit, hardware revision or firmware. A product missing here is not a statement that it is unaffected.

Scores, as their sources published them

DeSpy does not score records. These are the sources' own values.

Weaknesses

CWE-346

Sources

References the source lists

Source dates: published 2026-06-13, last changed 2026-07-23. DeSpy's copy of this version is dated 2026-09-28.

This product uses the NVD API but is not endorsed or certified by the NVD.

CVE records: Copyright © 1999-2026, The MITRE Corporation. CVE is a trademark and the CVE logo is a registered trademark of The MITRE Corporation.

CVE Usage: MITRE hereby grants you a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare derivative works of, publicly display, publicly perform, sublicense, and distribute Common Vulnerabilities and Exposures (CVE™). Any copy you make for such purposes is authorized provided that you reproduce MITRE's copyright designation and this license in any such copy.

CISA's Known Exploited Vulnerabilities catalog and CISA Vulnrichment data are CC0 1.0. CISA advisories are shown with the TLP label their document carries. No endorsement by CISA, DHS, NIST or MITRE is stated or implied.

Scope, sources and licences →