Google mcp-toolbox 1.4.0 Google OAuth provider ValidateMCPAuth mcpEnabled/audience/clientId improper authorization

Summaryinfo

A vulnerability classified as critical has been found in Google mcp-toolbox 1.4.0. The impacted element is the function ValidateMCPAuth of the component Google OAuth provider. This manipulation of the argument mcpEnabled/audience/clientId causes improper authorization. This vulnerability is registered as CVE-2026-14541. Remote exploitation of the attack is possible. No exploit is available.

Detailsinfo

A vulnerability classified as critical was found in Google mcp-toolbox 1.4.0. Affected by this vulnerability is the function ValidateMCPAuth of the component Google OAuth provider. The manipulation of the argument mcpEnabled/audience/clientId with an unknown input leads to a improper authorization vulnerability. The CWE definition for the vulnerability is CWE-285. The product does not perform or incorrectly performs an authorization check when an actor attempts to access a resource or perform an action. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a result, the toolbox will accept any valid Google OAuth access token—even those minted for unrelated ecosystem applications—granting unauthorized clients access to protected tools and data backends.

The advisory is shared at github.com. This vulnerability is known as CVE-2026-14541 since 07/03/2026. The exploitation appears to be easy. The attack can be launched remotely. Technical details are known, but no exploit is available. The price for an exploit might be around USD $5k-$25k at the moment (estimation calculated on 07/31/2026). MITRE ATT&CK project uses the attack technique T1548.002 for this issue.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• Google

Name

• mcp-toolbox

Version

• 1.4.0

License

• free

Website

• Vendor: https://www.google.com/

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion