CVE-2026-49857

high

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.

References

https://github.com/ymw0407/auth-fetch-mcp/security/advisories/GHSA-pvrj-8cg3-j5f8

https://github.com/ymw0407/auth-fetch-mcp/releases/tag/v3.0.1

https://github.com/ymw0407/auth-fetch-mcp/commit/c5c523cd55b24ae1680c5bacef95d59a81ae3450

Details

Source: Mitre, NVD

Published: 2026-08-13

Updated: 2026-08-13

Risk Information

CVSS v2

Base Score: 7.8

Vector: CVSS2#AV:N/AC:L/Au:N/C:C/I:N/A:N

Severity: High

CVSS v3

Base Score: 7.4

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:N/A:N

Severity: High

EPSS

EPSS: 0.00347