CVE-2026-39974
Full vulnerability record from the local CVENow database.
Description
n8n-MCP is a Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Prior to 2.47.4, an authenticated Server-Side Request Forgery in n8n-mcp allows a caller holding a valid AUTH_TOKEN to cause the server to issue HTTP requests to arbitrary URLs supplied through multi-tenant HTTP headers. Response bodies are reflected back through JSON-RPC, so an attacker can read the contents of any URL the server can reach — including cloud instance metadata endpoints (AWS IMDS, GCP, Azure, Alibaba, Oracle), internal network services, and any other host the server process has network access to. The primary at-risk deployments are multi-tenant HTTP installations where more than one operator can present a valid AUTH_TOKEN, or where a token is shared with less-trusted clients. Single-tenant stdio deployments and HTTP deployments without multi-tenant headers are not affected. This vulnerability is fixed in 2.47.4.
View original CVE JSON
{
"id": "CVE-2026-39974",
"sourceIdentifier": "[email protected]",
"published": "2026-04-09T17:16:30.933",
"lastModified": "2026-10-26T21:10:00.170",
"vulnStatus": "Analyzed",
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "n8n-MCP is a Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Prior to 2.47.4, an authenticated Server-Side Request Forgery in n8n-mcp allows a caller holding a valid AUTH_TOKEN to cause the server to issue HTTP requests to arbitrary URLs supplied through multi-tenant HTTP headers. Response bodies are reflected back through JSON-RPC, so an attacker can read the contents of any URL the server can reach — including cloud instance metadata endpoints (AWS IMDS, GCP, Azure, Alibaba, Oracle), internal network services, and any other host the server process has network access to. The primary at-risk deployments are multi-tenant HTTP installations where more than one operator can present a valid AUTH_TOKEN, or where a token is shared with less-trusted clients. Single-tenant stdio deployments and HTTP deployments without multi-tenant headers are not affected. This vulnerability is fixed in 2.47.4."
},
{
"lang": "es",
"value": "n8n-MCP es un servidor de Protocolo de Contexto de Modelo (MCP) que proporciona a los asistentes de IA acceso completo a la documentación, propiedades y operaciones de los nodos de n8n. Antes de la versión 2.47.4, una falsificación de petición del lado del servidor autenticada en n8n-mcp permite a un llamador que posee un AUTH_TOKEN válido hacer que el servidor emita peticiones HTTP a URLs arbitrarias suministradas a través de cabeceras HTTP multi-inquilino. Los cuerpos de respuesta se reflejan a través de JSON-RPC, por lo que un atacante puede leer el contenido de cualquier URL a la que el servidor pueda acceder, incluyendo puntos finales de metadatos de instancias en la nube (AWS IMDS, GCP, Azure, Alibaba, Oracle), servicios de red internos y cualquier otro host al que el proceso del servidor tenga acceso de red. Las implementaciones principales en riesgo son las instalaciones HTTP multi-inquilino donde más de un operador puede presentar un AUTH_TOKEN válido, o donde un token se comparte con clientes menos confiables. Las implementaciones stdio de un solo inquilino y las implementaciones HTTP sin cabeceras multi-inquilino no se ven afectadas. Esta vulnerabilidad está corregida en la versión 2.47.4."
}
],
"affected": [
{
"source": "[email protected]",
"affectedData": [
{
"vendor": "czlonkowski",
"product": "n8n-mcp",
"versions": [
{
"version": "< 2.47.4",
"status": "affected"
}
]
}
]
}
],
"metrics": {
"cvssMetricV31": [
{
"source": "[email protected]",
"type": "Secondary",
"cvssData": {
"version": "3.1",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N",
"baseScore": 8.5,
"baseSeverity": "HIGH",
"attackVector": "NETWORK",
"attackComplexity": "LOW",
"privilegesRequired": "LOW",
"userInteraction": "NONE",
"scope": "CHANGED",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"availabilityImpact": "NONE"
},
"exploitabilityScore": 3.1,
"impactScore": 4.7
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"timestamp": "2026-04-13T20:09:16.284220Z",
"id": "CVE-2026-39974",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"version": "2.0.3"
}
}
]
},
"weaknesses": [
{
"source": "[email protected]",
"type": "Secondary",
"description": [
{
"lang": "en",
"value": "CWE-918"
}
]
}
],
"configurations": [
{
"nodes": [
{
"operator": "OR",
"negate": false,
"cpeMatch": [
{
"vulnerable": true,
"criteria": "cpe:2.3:a:n8n-mcp:n8n-mcp:*:*:*:*:*:*:*:*",
"versionEndExcluding": "2.47.4",
"matchCriteriaId": "7CAAB9F8-4304-40CE-8A09-81BCE0D42741"
}
]
}
]
}
],
"references": [
{
"url": "https://github.com/czlonkowski/n8n-mcp/commit/d9d847f230923d96e0857ccecf3a4dedcc9b0096",
"source": "[email protected]",
"tags": [
"Patch"
]
},
{
"url": "https://github.com/czlonkowski/n8n-mcp/releases/tag/v2.47.4",
"source": "[email protected]",
"tags": [
"Release Notes"
]
},
{
"url": "https://github.com/czlonkowski/n8n-mcp/security/advisories/GHSA-4ggg-h7ph-26qr",
"source": "[email protected]",
"tags": [
"Vendor Advisory"
]
}
]
}