THREATOPS
THREAT OPS › Threat News › [GHSA] GHSA-rwrf-2pqf-9j8j (medium) — Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas

[GHSA] GHSA-rwrf-2pqf-9j8j (medium) — Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas

highgithub_advisoriesPublished 2026-10-27

GHSA-rwrf-2pqf-9j8j Severity: medium CVE: CVE-2026-116686

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

Indicators of compromise

Original source: https://github.com/advisories/GHSA-rwrf-2pqf-9j8j