---
title: "CVE-2026-48039: Meta Ads MCP: Unauthenticated HTTP MCP Tool Execution Leaks Operator Meta Access Token"
url: https://erroneo.us/security/cve/CVE-2026-48039/
description: "CVE-2026-48039 (meta-ads-mcp (PyPI)): Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-08-07
date_modified: 2026-08-07
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-48039"
kev: false
cvss: 9.1
epss: 0.00589
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-48039: Meta Ads MCP: Unauthenticated HTTP MCP Tool Execution Leaks Operator Meta Access Token

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.6% , percentile 47: FIRST’s model estimates a 0.6% chance of exploitation activity in the next 30 days, higher than 47% of all scored CVEs (low). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes meta-ads-mcp (PyPI) <= 1.0.108, fixed in 1.0.109 . Check your lockfile, including transitive dependencies.

## What it is

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 httpauthintegration.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 METAACCESSTOKEN 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 accesstoken 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

- PyPI `meta-ads-mcp` <= 1.0.108 → fixed: 1.0.109

## Affected products (CVE record)

- pipeboard-co meta-ads-mcp: < 1.0.109

## Severity

- GitHub_M CVSS 3.1: 9.1 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N`
- GitHub CVSS 3.1: 9.1 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 0.59% probability of exploitation activity in the next 30 days; percentile 47.

## Sources

- [GitHub Advisory GHSA-9gw6-46qc-99vr](https://github.com/advisories/GHSA-9gw6-46qc-99vr)
- [CVE.org record CVE-2026-48039](https://www.cve.org/CVERecord?id=CVE-2026-48039)
- [NVD entry CVE-2026-48039](https://nvd.nist.gov/vuln/detail/CVE-2026-48039)
- [github.com](https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr)
- [github.com](https://github.com/pipeboard-co/meta-ads-mcp/releases/tag/1.0.109)
- [github.com](https://github.com/pypa/advisory-database/tree/main/vulns/meta-ads-mcp/PYSEC-2026-413.yaml)

---
Source page: https://erroneo.us/security/cve/CVE-2026-48039/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt