CVE-2026-11624

The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new "--allowed-hosts" flag was introduced alongside the existing "--allowed-origins" flag, enabling users to specify permitted hosts at server startup. Both flags default to "*", allowing users to implement strict access controls as needed without breaking existing setups. If either flag is set to "*", the server will output a startup warning about potential vulnerabilities. Documentation has also been updated to highlight these security considerations.

CVSS

No CVSS.

References

Link	Resource
https://github.com/googleapis/mcp-toolbox/issues/3113
https://github.com/googleapis/mcp-toolbox/pull/2254

Configurations

No configuration.

History

23 Jul 2026, 09:10

Type	Values Removed	Values Added
Summary		(es) El Protocolo de Contexto del Modelo tiene una advertencia de seguridad que aconseja a los servidores validar el encabezado 'Origin' en todas las conexiones entrantes para prevenir ataques de revinculación de DNS. Antes del lanzamiento de la versión v0.25.0, los usuarios no tenían forma de validar el host del origen. En la versión v0.25.0, se introdujo una nueva bandera '--allowed-hosts' junto con la bandera '--allowed-origins' existente, lo que permite a los usuarios especificar hosts permitidos al inicio del servidor. Ambas banderas tienen un valor predeterminado de '', lo que permite a los usuarios implementar controles de acceso estrictos según sea necesario sin romper las configuraciones existentes. Si cualquiera de las banderas se establece en '', el servidor emitirá una advertencia de inicio sobre posibles vulnerabilidades. La documentación también se ha actualizado para destacar estas consideraciones de seguridad.

13 Jun 2026, 10:16

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-06-13 10:16

Updated : 2026-07-23 09:10

NVD link : CVE-2026-11624

Mitre link : CVE-2026-11624

CVE.ORG link : CVE-2026-11624

JSON object : View

Products Affected

No product.

CWE

CWE-346

Origin Validation Error

{"id": "CVE-2026-11624", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-11624", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-06-15T17:21:05.746230Z"}}], "cvssMetricV40": [{"type": "Secondary", "source": "cve-coordination@google.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 9.4, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "ACTIVE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "HIGH", "vulnIntegrityImpact": "HIGH", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "HIGH", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "HIGH", "vulnConfidentialityImpact": "HIGH", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "cve-coordination@google.com", "affectedData": [{"vendor": "Google", "product": "MCP Toolbox for Databases", "versions": [{"status": "affected", "version": "0", "lessThan": "0.25.0", "versionType": "semver"}], "defaultStatus": "unaffected"}]}], "published": "2026-06-13T10:16:17.700", "references": [{"url": "https://github.com/googleapis/mcp-toolbox/issues/3113", "source": "cve-coordination@google.com"}, {"url": "https://github.com/googleapis/mcp-toolbox/pull/2254", "source": "cve-coordination@google.com"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Secondary", "source": "cve-coordination@google.com", "description": [{"lang": "en", "value": "CWE-346"}]}], "descriptions": [{"lang": "en", "value": "The Model Context Protocol has a security warning advising servers to validate the \"Origin\" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new \"--allowed-hosts\" flag was introduced alongside the existing \"--allowed-origins\" flag, enabling users to specify permitted hosts at server startup. Both flags default to \"*\", allowing users to implement strict access controls as needed without breaking existing setups. If either flag is set to \"*\", the server will output a startup warning about potential vulnerabilities. Documentation has also been updated to highlight these security considerations."}, {"lang": "es", "value": "El Protocolo de Contexto del Modelo tiene una advertencia de seguridad que aconseja a los servidores validar el encabezado 'Origin' en todas las conexiones entrantes para prevenir ataques de revinculaci\u00f3n de DNS. Antes del lanzamiento de la versi\u00f3n v0.25.0, los usuarios no ten\u00edan forma de validar el host del origen. En la versi\u00f3n v0.25.0, se introdujo una nueva bandera '--allowed-hosts' junto con la bandera '--allowed-origins' existente, lo que permite a los usuarios especificar hosts permitidos al inicio del servidor. Ambas banderas tienen un valor predeterminado de '*', lo que permite a los usuarios implementar controles de acceso estrictos seg\u00fan sea necesario sin romper las configuraciones existentes. Si cualquiera de las banderas se establece en '*', el servidor emitir\u00e1 una advertencia de inicio sobre posibles vulnerabilidades. La documentaci\u00f3n tambi\u00e9n se ha actualizado para destacar estas consideraciones de seguridad."}], "lastModified": "2026-07-23T09:10:00.113", "sourceIdentifier": "cve-coordination@google.com"}