MCP TypeScript server SDK: Shared transport or server instances delivered one HTTP client's messages to another
CVE-2026-111770 · GHSA-jm63-cq47-j5jp · published 2026-10-20
- Severity
- High
- CVSS score
- 7.7
- Chance of exploitation (EPSS)
- 0.37%
- Fixed in
- 2.3.0
- Exploitation No known exploitation
- Automatable No
- Technical impact Partial
- CISA SSVC
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.
Upgrade @modelcontextprotocol/server to 2.3.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
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.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| @modelcontextprotocol/server | npm | >= 2.0.0, < 2.3.0 | 2.3.0 |
88 registered MCP servers install an affected version today, by the dependency versions a fresh install resolves.
- ai.ankimcp/anki-mcp-server@modelcontextprotocol/server@2.0.0
- ai.replylayer/replylayer@modelcontextprotocol/server@2.2.0
- ai.taasky/common-ground@modelcontextprotocol/server@2.0.0
- cash.gage/gage@modelcontextprotocol/server@2.0.0
- cloud.agkit/agkit@modelcontextprotocol/server@2.0.0
- com.50heads/mcp@modelcontextprotocol/server@2.0.0
- com.amplerun/gpu-rentals@modelcontextprotocol/server@2.1.0
- com.atlas-compiler/atlas@modelcontextprotocol/server@2.0.0
- com.klarefi/mcp@modelcontextprotocol/server@2.0.0
- com.mobilevalidate/mcp@modelcontextprotocol/server@2.0.0
- com.myrmigo/myrmigo@modelcontextprotocol/server@2.1.0
- com.parkerfawcett/rebuild-dossier@modelcontextprotocol/server@2.0.0
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
- HighMCP TypeScript SDK: HTTP server transports and handlers did not limit request body size or JSON-RPC batch length@modelcontextprotocol/hono, @modelcontextprotocol/node, @modelcontextprotocol/sdk, @modelcontextprotocol/server
- HighMCP TypeScript SDK: One HTTP request within the default size limit could exhaust server memory during validation@modelcontextprotocol/sdk, @modelcontextprotocol/server
- MediumMCP TypeScript SDK: Server bearer authentication accepted tokens issued for another service@modelcontextprotocol/express, @modelcontextprotocol/sdk, @modelcontextprotocol/server, @modelcontextprotocol/server-legacy
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.