CVE-2026-11624: CWE-346: Origin Validation Error in Google MCP Toolbox for Databases
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.
AI Analysis
Technical Summary
The Model Context Protocol (MCP) Toolbox for Databases had a security weakness where servers were advised to validate the "Origin" header on incoming connections to prevent DNS rebinding attacks. Before v0.25.0, users could not restrict allowed origins or hosts, leaving the server vulnerable. The release of v0.25.0 added the "--allowed-hosts" flag to complement the "--allowed-origins" flag, allowing users to specify permitted hosts at startup. Both flags default to "*", which means no restriction unless explicitly configured, and the server warns users if this default is used. This vulnerability is classified under CWE-346 (Origin Validation Error) and has a CVSS 4.0 score of 9.4, indicating critical severity.
Potential Impact
Without proper origin validation, the MCP Toolbox server is susceptible to DNS rebinding attacks, which can allow attackers to bypass same-origin policies and potentially access or manipulate internal resources. The lack of origin host validation prior to v0.25.0 means that servers running earlier versions are exposed to this risk. The introduction of configuration flags in v0.25.0 mitigates this by enabling administrators to restrict allowed origins and hosts, reducing the attack surface.
Mitigation Recommendations
Users should upgrade to version 0.25.0 or later, which introduces the "--allowed-hosts" and "--allowed-origins" flags to control access based on origin headers. Administrators must configure these flags to specify permitted hosts and origins explicitly rather than relying on the default "*" wildcard. The server issues a startup warning if either flag is set to "*", indicating potential vulnerability. Follow the updated documentation to implement strict access controls and prevent DNS rebinding attacks. Since no official patch beyond this configuration change is indicated, proper flag configuration is the primary mitigation.
CVE-2026-11624: CWE-346: Origin Validation Error in Google MCP Toolbox for Databases
Description
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.
CVSS v4.0
Score 9.4critical
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The Model Context Protocol (MCP) Toolbox for Databases had a security weakness where servers were advised to validate the "Origin" header on incoming connections to prevent DNS rebinding attacks. Before v0.25.0, users could not restrict allowed origins or hosts, leaving the server vulnerable. The release of v0.25.0 added the "--allowed-hosts" flag to complement the "--allowed-origins" flag, allowing users to specify permitted hosts at startup. Both flags default to "*", which means no restriction unless explicitly configured, and the server warns users if this default is used. This vulnerability is classified under CWE-346 (Origin Validation Error) and has a CVSS 4.0 score of 9.4, indicating critical severity.
Potential Impact
Without proper origin validation, the MCP Toolbox server is susceptible to DNS rebinding attacks, which can allow attackers to bypass same-origin policies and potentially access or manipulate internal resources. The lack of origin host validation prior to v0.25.0 means that servers running earlier versions are exposed to this risk. The introduction of configuration flags in v0.25.0 mitigates this by enabling administrators to restrict allowed origins and hosts, reducing the attack surface.
Mitigation Recommendations
Users should upgrade to version 0.25.0 or later, which introduces the "--allowed-hosts" and "--allowed-origins" flags to control access based on origin headers. Administrators must configure these flags to specify permitted hosts and origins explicitly rather than relying on the default "*" wildcard. The server issues a startup warning if either flag is set to "*", indicating potential vulnerability. Follow the updated documentation to implement strict access controls and prevent DNS rebinding attacks. Since no official patch beyond this configuration change is indicated, proper flag configuration is the primary mitigation.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- Date Reserved
- 2026-06-08T20:57:51.543Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a2d21c9e617e2d834ac3302
Added to database: 06/13/2026, 09:24:25 UTC
Last enriched: 06/20/2026, 16:03:53 UTC
Last updated: 07/19/2026, 17:26:46 UTC
Views: 246
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.