Vulnerability · Published Aug 7, 2026 · Assigned by GitHub_M
CVE-2026-48039Meta Ads MCP: Unauthenticated HTTP MCP Tool Execution Leaks Operator Meta Access Token
Critical 9.1
In plain English
A critical-severity improper authentication in meta-ads-mcp from pipeboard-co. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 48% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | meta-ads-mcp | 1.0.109 | GHSA-9gw6-46qc-99vr |
| PyPI | meta-ads-mcp | 1.0.109 | PYSEC-2026-413 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| pipeboard-co | meta-ads-mcp | < 1.0.109 |
Weakness: CWE-287 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N