Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-22jm-h49p-29qw

MCP TypeScript SDK: Experimental tasks were not tied to the session that created them

CVSS 8.6 HighEPSS 0.0034 · 28th percentile

Published by the GitHub Advisory Database at 20 Oct 2026, 18:26 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
@modelcontextprotocol/sdknpm>=1.24.0, <1.32.01.32.0
Identifiers
GHSA-22jm-h49p-29qw · CVE-2026-111767
Weakness (CWE)
CWE-639 · CWE-862
Tags
Published
20 Oct 2026
Updated
20 Oct 2026

Machine-written summary

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

The MCP TypeScript SDK (npm @modelcontextprotocol/sdk) versions 1.24.0 through 1.31.0 are affected through the experimental tasks feature, where the taskStore did not check which session created a task. An attacker who can connect to an HTTP server that passes taskStore to McpServer or Server, and whose clients share one InMemoryTaskStore, could list, read and cancel other clients' tasks. Upgrade to @modelcontextprotocol/sdk 1.32.0 or later, which ties each task to the session that created it; if you cannot upgrade, remove taskStore or create one InMemoryTaskStore per session.

Written 31 Oct 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
8.6 High 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:L CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0034, the 28th percentile, on 13 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 13:33 UTC First seen by agentprime
  2. 31 Oct 2026, 13:33 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.