AUGUST 15, 2026
Live Feed
Back to database
Case File

CVE-2026-49857

HIGH · CVSS 7.4 EPSS 0.35% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-08-13 · Last synced 2026-08-15

CyberRota Analysis

AI-Generated

The auth-fetch-mcp server in version 3.0.1 is vulnerable due to a flaw in its SSRF protection mechanism, which fails to correctly identify IPv4-mapped IPv6 loopback addresses, allowing attackers to bypass restrictions and access sensitive local services. This vulnerability poses a high risk, as it can be exploited without any special configuration changes. Organizations using this version should prioritize patching to mitigate potential unauthorized access to internal resources.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Detected Signals
exploit

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-49857
Severity
HIGH
CVSS
7.4
EPSS
0.35%

Original NVD Description

auth-fetch-mcp is an MCP server that lets AI assistants fetch content from authenticated web pages. Version 3.0.1 implements SSRF protection in `assertSafeUrl()` (`src/security.ts`) to block requests to private and loopback addresses. However, the `isPrivateV6()` function fails to detect IPv4-mapped IPv6 loopback addresses in their hex-normalized form. When an attacker supplies a URL such as `http://[::ffff:127.0.0.1]:PORT/`, the Node.js WHATWG URL parser silently normalizes the host to `[::ffff:7f00:1]`. Because `net.isIPv4('7f00:1')` returns `false`, the private-IP check is bypassed and the URL is passed to the browser or HTTP client, allowing the MCP tool to reach loopback services that are supposed to be blocked. The issue is exploitable under default configuration without any special environment variable. Version 3.0.1 patches the issue.