Skip to main content

MCP TypeScript server SDK: Shared transport or server instances delivered one HTTP client's messages to another (CVE-2026-111770)

0
High
Published: 10/20/2026 (10/20/2026, 20:07:29 UTC)
Source: GCVE Database
Product: @modelcontextprotocol/server

Description

A vulnerability in @modelcontextprotocol/server versions 2.0.0 through 2.2.0 allows an MCP server accessed over HTTP to deliver one client's responses and notifications to another client when clients share a stateless transport or a single server instance. This occurs because messages are matched only by JSON-RPC id, which can collide. The issue is fixed in version 2.3.0 and later, but requires code changes to avoid sharing SDK clients or server instances across multiple clients.

CVSS v3.1

Score 7.7high

Attack Vector
Network
Attack Complexity
High
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
Low
Availability
High
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:L/A:H

Affected software

npmghsa
@modelcontextprotocol/server
Affected versions
>=2.0.0 <2.3.0

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 10/20/2026, 22:43:09 UTC

Technical Analysis

In affected versions of @modelcontextprotocol/server (2.0.0 through 2.2.0), an MCP server reachable via HTTP could mistakenly deliver responses and notifications intended for one client to another client if multiple clients share a stateless transport or a single McpServer or Server instance. This is due to message matching relying solely on JSON-RPC id, which SDK clients number from zero, causing id collisions under normal use. The vulnerability does not affect stdio servers or SDK versions 1.26.0 and later. The issue is resolved in version 2.3.0 and later, which also introduces SDK behavior changes that prevent sharing client connections. Correct usage now requires creating a new McpServer and transport per request or session, or using a factory to build a new server on each call.

Potential Impact

An attacker or client could receive responses or notifications intended for another client, potentially exposing sensitive data or causing confusion in client-server communication. The CVSS score is 7.7 (high), reflecting network attack vector, high impact on confidentiality and availability, and low complexity but requiring high attack complexity due to the need to share the same server or transport instance.

Mitigation Recommendations

A fix is available in @modelcontextprotocol/server version 2.3.0 and later. Users must upgrade to this version and modify their code to avoid sharing SDK clients or server instances across multiple clients. Specifically, use createMcpHandler() with a factory that builds a new McpServer on every call, build a new McpServer and transport per request, or maintain one McpServer and transport per session with sessionIdGenerator configured. If upgrading is not immediately possible, applying these code changes to avoid shared instances also mitigates the issue.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Gcve Source
db.gcve.eu
Osv Id
GHSA-jm63-cq47-j5jp
Osv Schema Version
1.4.0
Aliases
["CVE-2026-111770"]
Ecosystems
["npm"]
Database Specific Severity
HIGH
Cvss Version
3.1

Threat ID: 6ad7ec462cdf04f6566b9f94

Added to database: 10/20/2026, 22:33:42 UTC

Last enriched: 10/20/2026, 22:43:09 UTC

Last updated: 10/20/2026, 22:43:09 UTC

Views: 5

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses