Vulnerability · Published Aug 13, 2026 · Assigned by GitHub_M

CVE-2026-49857auth-fetch-mcp has SSRF Protection Bypass via IPv4-mapped IPv6 Loopback

High 7.4

In plain English

A high-severity server-side request forgery in auth-fetch-mcp from ymw0407. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 42% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)7.4High
Exploit odds (30 days)0.5%top 57.8% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
npmauth-fetch-mcp3.0.2GHSA-pvrj-8cg3-j5f8

Affected products (as reported)

VendorProductVersions
ymw0407 auth-fetch-mcp < 3.0.2

Weakness: CWE-918 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:N/A:N

References