CVE-2026-111770: Model Context Protocol TypeScript SDK: Shared transport or server instances delivered one HTTP client's messages to another
Summary In affected versions, an MCP server reached over HTTP could deliver one client's responses and notifications to another client. This happened when clients shared one stateless transport, or one McpServer or Server instance.
Messages were matched to a connection by JSON-RPC id alone. SDK clients number requests from 0, so ids collide in normal use.
Am I affected? Yes, if more than one client can reach your HTTP endpoint and your code creates the transport or the server once at startup, instead of once per request or per session. Until this release, the README examples of @modelcontextprotocol/hono, express, fastify and node showed that pattern.
Affected versions: @modelcontextprotocol/server 2.0.0 through 2.2.0.
Not affected:
- createMcpHandler() with a factory that builds a new server on every call - stdio servers - @modelcontextprotocol/sdk 1.26.0 and later
Fix Upgrade to @modelcontextprotocol/server 2.3.0 or later.
You also need to change your code. The SDK now refuses to be shared, so an affected app fails requests after upgrading: a second connect() rejects with ALREADYCONNECTED, and a stateless transport rejects its second request.
Change to one of these:
- createMcpHandler(): pass a factory that builds a new McpServer on every call. - Per request: build a new McpServer and a new transport inside the request handler. - Per session: set sessionIdGenerator and keep one McpServer and one transport per session.
If you cannot upgrade yet, the same change fixes affected versions.
Other sources
The Model Context Protocol TypeScript SDK provides TypeScript client and server implementations of the Model Context Protocol. From 2.0.0 until 2.3.0 in @modelcontextprotocol/server, applications that shared one stateless HTTP transport or one McpServer or Server instance among multiple clients could deliver responses and notifications to the wrong client. The affected surface is an MCP server reached over HTTP by multiple clients. The trigger is reuse of one stateless transport or server instance. Messages were associated with a connection using only the JSON-RPC request identifier. SDK clients start request identifiers at zero, so collisions occur in normal operation. Cross-client delivery exposes one client's responses and notifications to another client. The issue requires an HTTP endpoint reachable by more than one client and an application that constructs the server or transport once at startup instead of once per request or session. stdio servers and factory-created per-call servers are not affected. Upgrading causes reused instances to fail and therefore requires an application code change. This issue is fixed in @modelcontextprotocol/server 2.3.0.
— MITRE
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
npm/@modelcontextprotocol/serverto a version that resolves this vulnerability.Fixed in 2.3.0 - Upgrade
Upgrade
@modelcontextprotocol/serverto a version that resolves this vulnerability.Fixed in 2.3.0 - Compensating control
Change the application code so shared server and transport instances are not reused across clients: for each request, build a new McpServer and transport inside the request handler; for each session, set sessionIdGenerator and keep one McpServer and one transport per session; and pass createMcpHandler() a factory that builds a new McpServer on every call.
Event History
Frequently Asked Questions
Which deployments are exposed to cross-client message delivery?
HTTP MCP endpoints are affected when more than one client can reach them and the application creates a transport, McpServer, or Server once at startup rather than per request or session. The README examples for @modelcontextprotocol/hono, express, fastify, and node used this affected pattern until this release.
What does an attacker need to exploit this issue?
An attacker needs network access to the HTTP MCP endpoint as a client. No privileges or user interaction are required; request IDs can collide during normal SDK client use because clients begin numbering requests at 0.
Are any configurations known not to be affected?
stdio servers are not affected. HTTP applications using createMcpHandler() with a factory that creates a new server for every call are also not affected, and @modelcontextprotocol/sdk 1.26.0 and later is listed as not affected.
What should be changed during remediation?
Upgrade @modelcontextprotocol/server to 2.3.0 or later and change the application to create a distinct server or transport per request or session. Upgrading without changing affected shared-instance code will cause requests to fail: a second connect() is rejected with ALREADY_CONNECTED, and a stateless transport rejects its second request.