UTC
Medium

Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas

CVE-2026-116686 · GHSA-rwrf-2pqf-9j8j · published 2026-10-27

Severity
Medium
CVSS score
6.5
Chance of exploitation (EPSS)
0.34%
Fixed in
2.2.0
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

In affected versions, when a connected MCP server declared an outputSchema for a tool, the SDK's client validated each call_tool result with jsonschema's default resolver, which fetches any $ref it cannot resolve locally by opening the URL. A server could therefore put an http://, https:// or file:// reference in a tool's output schema and make the client: request that URL, or read that local file, from the client's own network position on every call of the tool (the content was used only as a schema and never sent back to the server), and stall: the fetch ran synchronously on the event loop with no timeout, so a target that accepted the connection and then went quiet froze every session in…

What to do

Upgrade mcp to 2.2.0 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 mcp 1.30.0 (1.x) or 2.2.0 (2.x) or later. The client now resolves references only within the schema document the server sent (plus the standard JSON Schema metaschemas), so result validation performs no network or file access. A tool whose output schema points outside its own document fails at call time with RuntimeError (Invalid schema for tool ...); in-document references such as #/$defs/... work as before. Until you can upgrade, call tools only on servers you trust. As a partial stopgap, skip tools whose outputSchema contains an $id, or a $ref / $dynamicRef that does not start with #.

Affected
PackageRegistryAffectedFixed in
mcpPyPI>= 1.10.0, < 1.30.01.30.0
mcpPyPI>= 2.0.0, < 2.2.02.2.0
Downstream in the Official MCP Registry

43 registered MCP servers install an affected version today, by the dependency versions a fresh install resolves.

  • ai.datavidence/datavidence-financialsmcp@2.1.1
  • ai.solwyn/solwynmcp@2.1.1
  • com.browser-use/browser-usemcp@2.1.1
  • com.lucidlink/mcpmcp@2.0.0
  • com.nautaai/holster-mcpmcp@1.27.2
  • io.github.abhichandra21/promptheusmcp@1.12.4
  • io.github.Alejandrehl/kainext-binance-mcpmcp@1.29.0
  • io.github.amin-ale/mcp-quickbooksmcp@1.28.1
  • io.github.AndreySukhanov/summarix-telegrammcp@1.12.4
  • io.github.AS-XS/ai-pensieve-mcpmcp@2.1.1
  • io.github.ashlesh-t/cognirepomcp@1.27.0
  • io.github.astrogilda/waitbusmcp@1.28.1
All 43 servers on the trace →

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].