CVE-2026-48039
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
meta-ads-mcpPyPI | < 1.0.109 | 1.0.109 |
Affected products
1- Range: <= 1.0.108
Patches
Vulnerability mechanics
References
5- github.com/advisories/GHSA-9gw6-46qc-99vrghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-48039ghsaADVISORY
- github.com/pipeboard-co/meta-ads-mcp/releases/tag/1.0.109nvdWEB
- github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vrnvdWEB
- github.com/pypa/advisory-database/tree/main/vulns/meta-ads-mcp/PYSEC-2026-413.yamlnvdWEB
News mentions
0No linked articles in our index yet.