AWS HealthLake MCP Server SSRF via Unvalidated Pagination URL
UnratedCVE-2026-15643 · Published Jul 14, 2026 · updated Sep 22, 2026
Bulletin ID: 2026-054-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 07/14/2026 13:00 PM PDT Description: AWS HealthLake MCP Server (awslabs.healthlake-mcp-server) is a Model Context Protocol server that enables AI assistants to interact with AWS HealthLake FHIR datastores. We identified CVE-2026-15643 a server-side request forgery in the pagination handling component in AWS awslabs.healthlake-mcp-server before 0.0.14 on all platforms might allow a remote authenticated user to exfiltrate AWS temporary security credentials to an arbitrary endpoint via a crafted next_token parameter. The server does not validate that pagination URLs point back to the expected HealthLake endpoint, allowing an actor to redirect subsequent requests to an actor-controlled server. Impacted versions: Resolution: This issue has been addressed in awslabs.healthlake-mcp-server version 0.0.14 . We recommend upgrading to the latest version and ensuring any forked or derivative code is patched to incorporate the new fixes. Workarounds: In the interim, scope the IAM policy used by the server to least privilege rather than Resource: "*", and do not rely on the --readonly flag ...
Affected versions
Details and references
Bulletin ID: 2026-054-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 07/14/2026 13:00 PM PDT Description: AWS HealthLake MCP Server (awslabs.healthlake-mcp-server) is a Model Context Protocol server that enables AI assistants to interact with AWS HealthLake FHIR datastores. We identified CVE-2026-15643 a server-side request forgery in the pagination handling component in AWS awslabs.healthlake-mcp-server before 0.0.14 on all platforms might allow a remote authenticated user to exfiltrate AWS temporary security credentials to an arbitrary endpoint via a crafted next_token parameter. The server does not validate that pagination URLs point back to the expected HealthLake endpoint, allowing an actor to redirect subsequent requests to an actor-controlled server. Impacted versions: Resolution: This issue has been addressed in awslabs.healthlake-mcp-server version 0.0.14 . We recommend upgrading to the latest version and ensuring any forked or derivative code is patched to incorporate the new fixes. Workarounds: In the interim, scope the IAM policy used by the server to least privilege rather than Resource: "*", and do not rely on the --readonly flag as a security boundary — it is an in-process guard over the mutating tools, not an IAM control, so disclosed credentials retain their full granted authority. Operators using role-based (STS) deployments should consider rotating the affected role's credentials if they suspect using an affected version. References: CVE-2026-15643 GHSA-c5vr-x62j-w6rw Acknowledgement: We would like to thank Marios Gyftos for collaborating on this issue through the coordinated vulnerability disclosure process. Please email aws-security@amazon.com with any security questions or concerns. "},"metadata":{"tags":[]}},{"fields":{"patternBoolean2":"false","id":"ams#rt-rich-textc2#pattern-data"},"metadata":{"tags":[{"name":"pattern-data","description":"Default pattern data","id":"ams#rt-rich-textc2#pattern-data","namespaceId":"rt-rich-text"}]}}]},"metadata":{"auth":{},"testAttributes":{}},"context":{"page":{"pageUrl":"https://aws.amazon.com/security/security-bulletins/2026-054-aws/"},"contentType":"page","environment":{"stage":"prod","region":"us-west-2"},"sdkVersion":"2.0.27"},"refMap":{"manifest.js":"cda3e8d042","rt-rich-text.js":"5043b0a87f","rt-rich-text.rtl.css":"6a04028f86","rt-rich-text.css":"98f5a6aee4","rt-rich-text.css.js":"3d619cc2e1","rt-rich-text.rtl.css.js":"ccdb945d3e"},"settings":{"templateMappings":{"patternHeading":"patternHeading","patternSubheading":"patternSubheading","patternDark":"patternBoolean2","title":"itemHeading","bodyText":"itemLongLoc"}}} CVE-2026-15643 - AWS HealthLake MCP Server SSRF via Unvalidated Pagination URL Bulletin ID: 2026-054-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 07/14/2026 13:00 PM PDT Description: AWS HealthLake MCP Server (awslabs.healthlake-mcp-server) is a Model Context Protocol server that enables AI assistants to interact with AWS HealthLake FHIR datastores. We identified CVE-2026-15643 a server-side request forgery in the pagination handling component in AWS awslabs.healthlake-mcp-server before 0.0.14 on all platforms might allow a remote authenticated user to exfiltrate AWS temporary security credentials to an arbitrary endpoint via a crafted next_token parameter. The server does not validate that pagination URLs point back to the expected HealthLake endpoint, allowing an actor to redirect subsequent requests to an actor-controlled server. Impacted versions: Resolution: This issue has been addressed in awslabs.healthlake-mcp-server version 0.0.14 . We recommend upgrading to the latest version and ensuring any forked or derivative code is patched to incorporate the new fixes. Workarounds: In the interim, scope the IAM policy used by the server to least privilege rather than Resource: "*", and do not rely on the --readonly flag as a security boundary — it is an in-process guard over
- Severity from
- no source yet
More AWS advisories
All AWS| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Jul 17 | Path traversal and arbitrary file write in the workflow linters of... | Unrated | No fix yet |
| Jul 17 | Issue with Athena Federated Query Synapse Connector | Unrated | No fix yet |
| Jul 16 | Sensitive content disclosure via OpenTelemetry spans in AgentCore Python SDK | Unrated | No fix yet |
| Jul 15 | OS command injection in jsii-diff in AWS jsii | Unrated | No fix yet |
| Jul 15 | Credential disclosure in Strands Agents Tools elasticsearch_memory tool | Unrated | No fix yet |
| Jul 14 | aws-load-balancer-controller: insufficient isolation | Medium5.8 | 3.4.2 |