CVE-2026-16481: CWE-918: Server-Side Request Forgery (SSRF) in Google MCP Toolbox for Databases (googleapis/mcp-toolbox)
A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox. The tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorization: Bearer header to every outbound request regardless of the destination host. An attacker can supply an arbitrary external URL to the pageURL parameter (either directly via the tool execution payload or implicitly via data-driven pagination tracking loops), leading Toolbox into sending its OAuth/service-account access token to an attacker-controlled listener. Depending on the configuration, this leaks either the end-user's token or the broader service-account access token (ADC), potentially exposing Protected Health Information (PHI) and secondary Google Cloud Platform services.
AI Analysis
Technical Summary
The vulnerability in googleapis/mcp-toolbox (version 0.19.1) involves the cloud-healthcare-fhir-fetch-page tool accepting an unvalidated pageURL parameter from clients. When the tool issues an HTTP GET request to this URL, it automatically includes an Authorization: Bearer header containing OAuth or service-account tokens. An attacker can exploit this by supplying a malicious external URL, causing the tool to send sensitive tokens to an attacker-controlled endpoint. This SSRF vulnerability can lead to credential exfiltration and exposure of PHI and other cloud resources. The affected product is a cloud-hosted service, and the vendor manages remediation server-side. A patch is available, but specific patch details are not provided in the advisory.
Potential Impact
Successful exploitation allows an attacker to obtain OAuth or service-account access tokens by tricking the tool into sending authenticated requests to attacker-controlled URLs. This can lead to unauthorized access to Protected Health Information (PHI) and other Google Cloud Platform services, posing a significant confidentiality risk. The CVSS 4.0 score of 8.4 (high severity) reflects the network attack vector, low attack complexity, no user interaction, and high impact on confidentiality and system integrity.
Mitigation Recommendations
Since this is a cloud-hosted service, Google manages remediation server-side. A patch is available for the vulnerability. Users should monitor the vendor advisory for deployment status and ensure they are using updated versions or configurations as recommended by Google. No additional user action is specified in the advisory.
CVE-2026-16481: CWE-918: Server-Side Request Forgery (SSRF) in Google MCP Toolbox for Databases (googleapis/mcp-toolbox)
Description
A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox. The tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorization: Bearer header to every outbound request regardless of the destination host. An attacker can supply an arbitrary external URL to the pageURL parameter (either directly via the tool execution payload or implicitly via data-driven pagination tracking loops), leading Toolbox into sending its OAuth/service-account access token to an attacker-controlled listener. Depending on the configuration, this leaks either the end-user's token or the broader service-account access token (ADC), potentially exposing Protected Health Information (PHI) and secondary Google Cloud Platform services.
CVSS v4.0
Score 6.0medium
Affected software
MCP Toolbox for Databases (googleapis/mcp-toolbox)
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability in googleapis/mcp-toolbox (version 0.19.1) involves the cloud-healthcare-fhir-fetch-page tool accepting an unvalidated pageURL parameter from clients. When the tool issues an HTTP GET request to this URL, it automatically includes an Authorization: Bearer header containing OAuth or service-account tokens. An attacker can exploit this by supplying a malicious external URL, causing the tool to send sensitive tokens to an attacker-controlled endpoint. This SSRF vulnerability can lead to credential exfiltration and exposure of PHI and other cloud resources. The affected product is a cloud-hosted service, and the vendor manages remediation server-side. A patch is available, but specific patch details are not provided in the advisory.
Potential Impact
Successful exploitation allows an attacker to obtain OAuth or service-account access tokens by tricking the tool into sending authenticated requests to attacker-controlled URLs. This can lead to unauthorized access to Protected Health Information (PHI) and other Google Cloud Platform services, posing a significant confidentiality risk. The CVSS 4.0 score of 8.4 (high severity) reflects the network attack vector, low attack complexity, no user interaction, and high impact on confidentiality and system integrity.
Mitigation Recommendations
Since this is a cloud-hosted service, Google manages remediation server-side. A patch is available for the vulnerability. Users should monitor the vendor advisory for deployment status and ensure they are using updated versions or configurations as recommended by Google. No additional user action is specified in the advisory.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- Date Reserved
- 2026-07-21T14:56:59.820Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Is Cloud Service
- true
Threat ID: 6a67b0129c2644c7f8ad2d19
Added to database: 07/27/2026, 19:22:58 UTC
Last enriched: 07/30/2026, 00:59:42 UTC
Last updated: 09/10/2026, 22:12:32 UTC
Views: 119
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.
External Links
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.