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.
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@modelcontextprotocol/sdk 1.26.0 and laterUpgrade 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 ALREADY_CONNECTED, 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.McpServer and a new transport inside the request handler.sessionIdGenerator and keep one McpServer and one transport per session.If you cannot upgrade yet, the same change fixes affected versions.
{
"cwe_ids": [
"CWE-362"
],
"github_reviewed": true,
"github_reviewed_at": "2026-10-20T20:07:29Z",
"nvd_published_at": null,
"severity": "HIGH"
}