PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-14540 Google CVE debrief

A Server-Side Request Forgery (SSRF) vulnerability exists in Google mcp-toolbox versions 0.3.0 through 1.4.0. The underlying HTTP client fails to safely regulate request redirection boundaries due to a lack of restrictive CheckRedirect policy hook and target IP validation. This allows an attacker to supply a crafted path parameter that triggers an open redirect or direct destination swap, coercing the mcp-toolbox into making unauthorized requests to internal or arbitrary external endpoints.

Vendor
Google
Product
mcp-toolbox
CVSS
HIGH 8
CISA KEV
Not listed in stored evidence
Original CVE published
2026-07-31
Original CVE updated
2026-08-08
Advisory published
2026-07-31
Advisory updated
2026-08-08

Who should care

Security teams and administrators responsible for Google mcp-toolbox versions 0.3.0 through 1.4.0 should be aware of this vulnerability and take necessary actions to mitigate the risk. This includes operators managing affected deployments, platform administrators, vulnerability management teams, and security teams responsible for monitoring and incident response.

Technical summary

The Google mcp-toolbox versions 0.3.0 through 1.4.0 contain a Server-Side Request Forgery (SSRF) vulnerability. The vulnerability exists due to the underlying HTTP client not safely regulating request redirection boundaries. This is caused by the lack of a restrictive CheckRedirect policy hook and target IP validation. An attacker can exploit this by supplying a crafted path parameter that triggers an open redirect or direct destination swap. This forces the mcp-toolbox to make unauthorized requests to internal or arbitrary external endpoints.

Defensive priority

High priority due to the potential for unauthorized requests to internal or external endpoints.

Recommended defensive actions

  • Implement restrictive CheckRedirect policy hook
  • Add target IP validation
  • Review and update input sanitization for user-controlled parameters
  • Monitor for suspicious activity
  • Apply vendor remediation when available
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented

Evidence notes

Evidence is limited; further verification is needed to determine the full scope of affected systems, potential impact, and what defenders should verify. The underlying HTTP client fails to safely regulate request redirection boundaries due to a lack of restrictive CheckRedirect policy hook and target IP validation.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-14540 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-14540

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-14540 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-14540

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.