UTC
Medium

MCP TypeScript SDK: Server bearer authentication accepted tokens issued for another service

CVE-2026-111771 · GHSA-rvq5-wwqv-78pq · published 2026-10-20

Severity
Medium
CVSS score
6.8
Chance of exploitation (EPSS)
0.54%
Fixed in
2.0.2
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

In affected versions, the SDK's server-side bearer authentication had no way to check that a token was issued for your server (its audience). Where one authorization server issues tokens for several services, a valid token for another service was also accepted by your MCP server.

What to do

Upgrade @modelcontextprotocol/express to 2.0.2 or later, and @modelcontextprotocol/sdk to 1.32.0 or later, and @modelcontextprotocol/server to 2.3.0 or later, and @modelcontextprotocol/server-legacy to 2.3.1 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: 1.x: @modelcontextprotocol/sdk 1.32.0 or later 2.x: @modelcontextprotocol/server 2.3.0 or later, together with @modelcontextprotocol/express 2.0.2 or later if you use it @modelcontextprotocol/server-legacy 2.3.1 or later Upgrading alone changes nothing. The patched versions add an expectedResource setting that is off by default. To turn the check on, make both of these changes together: 1. Pass the audience your authorization server puts in tokens for your server: . A token for another service then gets 401. With only the first change, every request gets 401. If you cannot upgrade yet, reject any token whose aud does not include your server inside verifyAccessToken().

Affected
PackageRegistryAffectedFixed in
@modelcontextprotocol/expressnpm>= 2.0.0, < 2.0.22.0.2
@modelcontextprotocol/sdknpm>= 1.6.0, < 1.32.01.32.0
@modelcontextprotocol/servernpm>= 2.0.0, < 2.3.02.3.0
@modelcontextprotocol/server-legacynpm>= 2.0.0, < 2.3.12.3.1
Downstream in the Official MCP Registry

443 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.kloudy/kloudy@modelcontextprotocol/sdk@1.31.0
  • ai.makerportal/compute@modelcontextprotocol/sdk@1.30.0
  • ai.maxwellinternational/data@modelcontextprotocol/sdk@1.31.0
  • ai.mentu/navigator@modelcontextprotocol/sdk@1.29.0
  • ai.myspaice/spaces@modelcontextprotocol/sdk@1.29.0
  • ai.replylayer/replylayer@modelcontextprotocol/server@2.2.0
  • ai.sanctuaryprotocol/sanctuary@modelcontextprotocol/sdk@1.30.0
  • ai.satohub/kit@modelcontextprotocol/sdk@1.30.1
  • ai.sendshort/sendshort@modelcontextprotocol/sdk@1.30.0
  • ai.taasky/common-ground@modelcontextprotocol/server@2.0.0
  • app.somiya/mcp@modelcontextprotocol/sdk@1.30.0
All 443 servers on the trace →
Also in @modelcontextprotocol/express, @modelcontextprotocol/sdk, @modelcontextprotocol/server, @modelcontextprotocol/server-legacy
  1. 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
  2. HighMCP TypeScript SDK: Experimental tasks were not tied to the session that created them@modelcontextprotocol/sdk
  3. HighMCP TypeScript SDK: One HTTP request within the default size limit could exhaust server memory during validation@modelcontextprotocol/sdk, @modelcontextprotocol/server
  4. HighMCP TypeScript server SDK: Shared transport or server instances delivered one HTTP client's messages to another@modelcontextprotocol/server
  5. HighMCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server@modelcontextprotocol/client, @modelcontextprotocol/sdk
  6. High@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse@modelcontextprotocol/sdk

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.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].