← Back to CVE Explorer

CVE-2026-48039

Full vulnerability record from the local CVENow database.

Description

Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` unconditionally forwards unauthenticated Streamable HTTP requests to downstream MCP tool handlers without issuing a `401` response, allowing any network-reachable caller to invoke MCP tools without authentication. When no per-request credential is present, tool handlers fall back to the `META_ACCESS_TOKEN` environment variable, and when the downstream Meta Graph API call fails, `api.py:263–269` serialises the raw `httpx` request URL—including the operator's `access_token` as a query parameter—into the JSON-RPC response body, delivering the credential to the unauthenticated caller. Version 1.0.109 fixes the issue.

Severity
CRITICAL
CVSS score
9.1 (v3.1)
Vulnerability status
Deferred
Source identifier
Published
2026-08-07 20:16:51.723000
Last modified
2026-10-23 20:10:00.160000
View original CVE JSON
{
  "id": "CVE-2026-48039",
  "sourceIdentifier": "[email protected]",
  "published": "2026-08-07T20:16:51.723",
  "lastModified": "2026-10-23T20:10:00.160",
  "vulnStatus": "Deferred",
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` unconditionally forwards unauthenticated Streamable HTTP requests to downstream MCP tool handlers without issuing a `401` response, allowing any network-reachable caller to invoke MCP tools without authentication. When no per-request credential is present, tool handlers fall back to the `META_ACCESS_TOKEN` environment variable, and when the downstream Meta Graph API call fails, `api.py:263–269` serialises the raw `httpx` request URL—including the operator's `access_token` as a query parameter—into the JSON-RPC response body, delivering the credential to the unauthenticated caller. Version 1.0.109 fixes the issue."
    },
    {
      "lang": "es",
      "value": "Meta Ads MCP es un servidor de Protocolo de Contexto de Modelo (MCP) que permite a los asistentes de IA ejecutar Meta Ads. Antes de la versión 1.0.109, “AuthInjectionMiddleware.dispatch()” en “http_auth_integration.py:272” reenvía incondicionalmente las solicitudes HTTP transmitibles no autenticadas a los manejadores de herramientas MCP posteriores sin emitir una respuesta “401”, permitiendo a cualquier llamador accesible por red invocar herramientas MCP sin autenticación. Cuando no hay una credencial por solicitud presente, los manejadores de herramientas recurren a la variable de entorno “META_ACCESS_TOKEN”, y cuando la llamada a la API de Meta Graph posterior falla, “api.py:263-269” serializa la URL de solicitud “httpx” sin procesar -incluyendo el “access_token” del operador como un parámetro de consulta- en el cuerpo de la respuesta JSON-RPC, entregando la credencial al llamador no autenticado. La versión 1.0.109 soluciona el problema."
    }
  ],
  "affected": [
    {
      "source": "[email protected]",
      "affectedData": [
        {
          "vendor": "pipeboard-co",
          "product": "meta-ads-mcp",
          "versions": [
            {
              "version": "< 1.0.109",
              "status": "affected"
            }
          ]
        }
      ]
    }
  ],
  "metrics": {
    "cvssMetricV31": [
      {
        "source": "[email protected]",
        "type": "Secondary",
        "cvssData": {
          "version": "3.1",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N",
          "baseScore": 9.1,
          "baseSeverity": "CRITICAL",
          "attackVector": "NETWORK",
          "attackComplexity": "LOW",
          "privilegesRequired": "NONE",
          "userInteraction": "NONE",
          "scope": "UNCHANGED",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "availabilityImpact": "NONE"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 5.2
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "timestamp": "2026-08-07T19:41:49.858751Z",
          "id": "CVE-2026-48039",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "version": "2.0.3"
        }
      }
    ]
  },
  "weaknesses": [
    {
      "source": "[email protected]",
      "type": "Primary",
      "description": [
        {
          "lang": "en",
          "value": "CWE-287"
        }
      ]
    }
  ],
  "references": [
    {
      "url": "https://github.com/pipeboard-co/meta-ads-mcp/releases/tag/1.0.109",
      "source": "[email protected]"
    },
    {
      "url": "https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr",
      "source": "[email protected]"
    },
    {
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/meta-ads-mcp/PYSEC-2026-413.yaml",
      "source": "[email protected]"
    },
    {
      "url": "https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ]
}