Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas
Summary
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 $ref it cannot resolve locally by opening the URL. A server could therefore put an http://, https:// or file:// reference in a tool's output schema and make the client:
- request that URL, or read that local file, from the client's own network position on every call of the tool (the content was used only as a schema and never sent back to the server), and
- stall: the fetch ran synchronously on the event loop with no timeout, so a target that accepted the connection and then went quiet froze every session in the process for as long as it held the connection.
Am I affected?
Yes, if your application uses the SDK as an MCP client (ClientSession over any transport, ClientSessionGroup, or the 2.x Client) and calls tools on servers you do not fully control. There was no setting that turned the validation off.
Affected versions: 1.10.0 through 1.29.1, and 2.0.0 through 2.1.1.
Not affected: applications that only build servers. If nothing in your code uses ClientSession, ClientSessionGroup or the 2.x Client class, you are not affected.
Fix
Upgrade to mcp 1.30.0 (1.x) or 2.2.0 (2.x) or later. The client now resolves references only within the schema document the server sent (plus the standard JSON Schema metaschemas), so result validation performs no network or file access. A tool whose output schema points outside its own document fails at call time with RuntimeError (Invalid schema for tool ...); in-document references such as #/$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 #.
Betroffene Software
Klicken Sie auf eine Technologie, um alle zugehörigen Schwachstellen anzuzeigen.
| Plattform | Paket | Anfällige Versionen | Behoben in |
|---|---|---|---|
| Python (PyPI) | mcp | >= 2.0.0, < 2.2.0, >= 1.10.0, < 1.30.0 | 2.2.0, 1.30.0 |
Verweise
- https://github.com/modelcontextprotocol/python-sdk/security/advisories/GHSA-rwrf-2pqf-9j8j
- https://github.com/modelcontextprotocol/python-sdk/pull/3394
- https://github.com/modelcontextprotocol/python-sdk/pull/3396
- https://github.com/modelcontextprotocol/python-sdk/commit/5ebdfed4060d8e5b11b8e2348f86bad4d1fb8836
- https://github.com/modelcontextprotocol/python-sdk/commit/6705402e246dc4eb1fcdf4d9902b78d3c9c36e1b
- https://github.com/modelcontextprotocol/python-sdk
- https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.30.0
- https://github.com/modelcontextprotocol/python-sdk/releases/tag/v2.2.0
- CVSS-Vektor
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H- Schwäche (CWE)
CWE-918- Plattform
- Python (PyPI)
- Paket
mcp- Veröffentlicht
- 27.10.2026
- Aktualisiert
- 27.10.2026 23:17
Quellen und Lizenzen
OSV / GitHub Advisory Database - GHSA-rwrf-2pqf-9j8j - CC BY 4.0
Schwachstellenhistorie: mcp
Alle veröffentlichten Schwachstellen dieses Pakets (Python (PyPI)), neueste zuerst. Zeigt, ob es ein einmaliger Ausrutscher ist oder ein Paket, das man im Auge behalten muss.
- Einträge insgesamt
- 11
- Erste → letzte
- 07.2025 11.2026
- Ohne Fix
- 0
- In Angriffen ausgenutzt
- 0
Verteilung nach Schweregrad
- Hoch 7
- Mittel 4
Veröffentlichungen pro Jahr
- 2025: 3
- 2026: 8
-
Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas dieser Eintrag
Erkennen Sie Schwachstellen in Ihrer Anwendung
Mit der DockRay-Integration und aktivierter Softwareinventarisierung prüft DockRay gemeldete Komponentenversionen auf bekannte Schwachstellen und benachrichtigt Sie über bestätigte Treffer. Die Abdeckung hängt von der unterstützten Technologie und den verfügbaren Meldungen ab.