Mcp Fetch
Monthly
Server-Side Request Forgery in mcp-fetch through version 1.6.3 allows unauthenticated attackers who can influence model tool arguments to bypass the SSRF guard entirely and reach loopback, private, and link-local network endpoints including cloud instance metadata services. The bypass exploits a parsing gap: the guard tests the bracketed IPv6 literal string such as [::1] against Node.js's net.isIP(), which returns zero for bracketed input, causing the private-address branch to be skipped; the HTTP client later strips the brackets and connects normally. A secondary flaw in isPrivateIPv6 - no handling of the ::ffff: IPv4-mapped prefix - provides an independent bypass path for IPv4 targets expressed in mapped form. No public exploit code or CISA KEV listing exists at time of analysis, though a public issue report documenting the flaw is open on the upstream repository.
Server-Side Request Forgery in mcp-fetch through version 1.6.3 allows unauthenticated attackers who can influence model tool arguments to bypass the SSRF guard entirely and reach loopback, private, and link-local network endpoints including cloud instance metadata services. The bypass exploits a parsing gap: the guard tests the bracketed IPv6 literal string such as [::1] against Node.js's net.isIP(), which returns zero for bracketed input, causing the private-address branch to be skipped; the HTTP client later strips the brackets and connects normally. A secondary flaw in isPrivateIPv6 - no handling of the ::ffff: IPv4-mapped prefix - provides an independent bypass path for IPv4 targets expressed in mapped form. No public exploit code or CISA KEV listing exists at time of analysis, though a public issue report documenting the flaw is open on the upstream repository.