CVE-2026-14541: Google mcp-toolbox · (Improper Authentication)
Affects Google mcp-toolboxSource CVE Database V5
Not known to be exploited · CVSS 8.0 High.
Data as of 29 Oct 2026, 07:15 UTC
- EPSS
- 0.2% chance of exploitation in 30 days – higher than 16% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:UExploitation evidence
Disclosed: evidence found.
CVE published 31 Jul 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 29 Oct 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| Googlemcp-toolbox | Affected
| Fixed in– |
AI-suggested
Until a fix is available, ensure that the Google OAuth provider component is configured with an explicit audience or clientId when mcpEnabled is true to enforce proper token audience validation.
Description
CVE-2026-14541 is an authentication bypass vulnerability in Google mcp-toolbox version 1.4.0. The flaw occurs when the Google OAuth provider component is initialized with mcpEnabled set to true but without an explicitly defined audience or clientId. This causes the ValidateMCPAuth pipeline to skip audience validation for opaque tokens, allowing acceptance of any valid Google OAuth access token, even those intended for unrelated applications. This can grant unauthorized access to protected tools and data backends.