Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-xw59-hvm2-8pj6

DNS Rebinding Protection Disabled by Default in Model Context Protocol Go SDK for Servers Running on Localhost

CVSS 7.6 HighEPSS 0.0047 · 41st percentile

Published by the GitHub Advisory Database at 1 Apr 2026, 21:09 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
github.com/modelcontextprotocol/go-sdkGo<1.4.01.4.0
Identifiers
GHSA-xw59-hvm2-8pj6 · CVE-2026-34742 · GO-2026-5771
Weakness (CWE)
CWE-1188
Tags
Published
1 Apr 2026
Updated
21 Jul 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

Versions of the Go github.com/modelcontextprotocol/go-sdk package before 1.4.0 do not enable DNS rebinding protection by default for HTTP-based servers. An attacker who lures a user to a malicious website could use DNS rebinding to send requests to an MCP server running on localhost without authentication, invoking its tools or accessing its resources. Upgrade to version 1.4.0, which enables this protection by default for servers bound to localhost. Stdio-transport servers are not affected.

Written 6 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
7.6 High 4.0 CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0047, the 41st percentile, on 7 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 15:05 UTC First seen by agentprime
  2. 31 Oct 2026, 15:05 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.