CVE-2026-54549
HighCVSS 8.3Summary
In Meta Ads MCP before 1.0.115, the upload_ad_image tool in meta_ads_mcp/core/ads.py passes an attacker-controlled image_url to try_multiple_download_methods() in meta_ads_mcp/core/utils.py, where httpx.AsyncClient uses follow_redirects=True and performs HTTP requests without validating the scheme, host, or resolved IP address. In a streamable-http deployment, a network caller can use any non-empty authorization value because Meta credential validation occurs after the image download, then direct the server to loopback services, private-network addresses, cloud metadata endpoints, or redirect-chained internal targets. The resulting server-side request forgery can expose internal data, invoke state-changing internal services, or disrupt reachable services. Fixed in version 1.0.115.
Risk Assessment
An unauthenticated attacker can exploit the SSRF vulnerability to access internal services, expose data, or invoke state-changing operations. This may lead to compromise of internal infrastructure and disruption of services.
Recommendation
Upgrade Meta Ads MCP to version 1.0.115, which validates the scheme, host, and resolved IP address. Until patched, consider restricting network access to the MCP server or disabling the upload_ad_image tool.
Other vulnerabilities in Meta Ads MCP
See all- CVE-2026-54547High
Meta Ads MCP prior to version 1.0.115 contains a flaw in AuthInjectionMiddleware that rejects HTTP requests only when both tokens are absent, while extract_token_from_headers() does not recognize X-Pipeboard-Token as a primary credential. A remote caller using the streamable-http transport can send any X-Pipeboard-Token value, bypass the guard, and cause the server to fall back to the operator's META_ACCESS_TOKEN.
- CVE-2026-48039Critical
Meta Ads MCP prior to version 1.0.109 has a vulnerability in AuthInjectionMiddleware.dispatch() that 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, the JSON-RPC response body includes the raw request URL with the access token, exposing the credential to the unauthenticated caller.
Original NVD description (English source)
Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.115, the upload_ad_image tool in meta_ads_mcp/core/ads.py passes an attacker-controlled image_url to try_multiple_download_methods() in meta_ads_mcp/core/utils.py, where httpx.AsyncClient uses follow_redirects=True and performs HTTP requests without validating the scheme, host, or resolved IP address. In a streamable-http deployment, a network caller can use any non-empty authorization value because Meta credential validation occurs after the image download, then direct the server to loopback services, private-network addresses, cloud metadata endpoints, or redirect-chained internal targets. The resulting server-side request forgery can expose internal data, invoke state-changing internal services, or disrupt reachable services. This issue is fixed in version 1.0.115.