Read the docs

Model Context Protocol Python SDK sends credentials across redirects

Priority LOW 27CWE-200Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
High
Impact type
Information disclosure
Confidentiality · integrity · availability
High · None · None
Fix status
Partial Red Hat: 12 without a fix

Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-200.

Summary

Model Context Protocol Python SDK versions from 1.8.0 before 1.30.0 and from 2.0.0 before 2.2.0 are affected. Its HTTP client transports follow redirects to a different origin and forward caller-supplied custom credential headers, and request bodies for 307 or 308 responses, to that destination. This exposes sensitive information (CWE-200). An attacker who can influence a trusted endpoint's redirect destination can receive that material.

Written with Claude Haiku 5.5 from the sources below · 2026-11-06

Description from the CNA

The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.8.0 until 1.30.0 and 2.2.0, streamable_http_client, streamablehttp_client, sse_client, ClientSessionGroup, OAuth, and create_mcp_http_client client paths enable follow_redirects and follow redirects to a different origin, forwarding caller-supplied custom credential headers and, for 307 or 308 responses, the request body. An attacker who can influence a trusted endpoint's redirect destination can receive that material. This issue is fixed in versions 1.30.0 and 2.2.0.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00399 34th percentileScored 2026-11-07
Fix Partial python-sdk (modelcontextprotocol): 1.30.0, 2.2.0mcp (PyPI): 2.2.0, 1.30.0Red Hat: 12 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
MLflowpython-sdk1.8.0 to before 1.30.0; 2.0.0 to before 2.2.01.30.0, 2.2.0Patch availableCNA
—mcp (PyPI)2.0.0 to before 2.2.02.2.0Patch availableGHSA-5h93-6whr-6q8j
—mcp (PyPI)1.8.0 to before 1.30.01.30.0Patch availableGHSA-5h93-6whr-6q8j
  • python-sdk VendorMLflow Affected 1.8.0 to before 1.30.0; 2.0.0 to before 2.2.0 Fixed in 1.30.0, 2.2.0 Patch available CNA
  • mcp (PyPI) Vendor— Affected 2.0.0 to before 2.2.0 Fixed in 2.2.0 Patch available GHSA-5h93-6whr-6q8j
  • mcp (PyPI) Vendor— Affected 1.8.0 to before 1.30.0 Fixed in 1.30.0 Patch available GHSA-5h93-6whr-6q8j

CPE names Threatist (inferred) · 1

Inferred from how NVD named this product before; not given by a source.

CPEVersionsRoleVendor
cpe:2.3:a:lfprojects:mcp_python_sdk:*:*:*:*:*:*:*:*——MLflow
  • cpe:2.3:a:lfprojects:mcp_python_sdk:*:*:*:*:*:*:*:* Versions — — ·MLflow

Remediation

Upgrade the modelcontextprotocol python-sdk package to version 1.30.0 for the 1.x line or 2.2.0 for the 2.x line, and the mcp PyPI package to the same versions. The sources list no fixed version for Ansible Automation Orchestrator 2026, Lightspeed Core, Migration Toolkit for Applications 8, OpenShift Lightspeed, Red Hat AI Inference Server, Red Hat Ansible Automation Platform 2, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat Enterprise Linux command line assistant, Red Hat OpenShift AI (RHOAI), Red Hat OpenShift Virtualization 4 and Red Hat Satellite 6, and no fix planned for Exploit Intelligence.

Written with Claude Haiku 5.5 from the sources below · 2026-11-06

  • Fix · CNA python-sdk (modelcontextprotocol) Fixed in 1.30.0, 2.2.0
  • Fix · GHSA-5h93-6whr-6q8j mcp (PyPI) Fixed in 2.2.0 Advisory →
  • Fix · GHSA-5h93-6whr-6q8j mcp (PyPI) Fixed in 1.30.0 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

ProductStatusPlan or fix
Ansible Automation Orchestrator 2026AffectedNo fix yet: Fix deferred
Exploit IntelligenceAffectedNo fix planned: Out of support scope
Lightspeed CoreAffectedNo fix yet: Fix deferred
Migration Toolkit for Applications 8AffectedNo fix yet: Fix deferred
OpenShift LightspeedAffectedNo fix yet: Fix deferred
Red Hat AI Inference ServerAffectedNo fix yet: Fix deferred
Red Hat Ansible Automation Platform 2AffectedNo fix yet: Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix yet: Fix deferred
Red Hat Enterprise Linux command line assistantAffectedNo fix yet: Fix deferred
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet: Fix deferred
Red Hat OpenShift Virtualization 4AffectedNo fix yet: Fix deferred
Red Hat Satellite 6AffectedNo fix yet: Fix deferred

Timeline

  1. 2026-10-27 Threatist record created from CVE-2026-116685
  2. 2026-10-27 Alias added: GHSA-5h93-6whr-6q8j
  3. 2026-10-28 Priority changed: MEDIUM → LOW
  4. 2026-10-30 CISA SSVC decision points changed
  5. 2026-11-06 Affected versions changed · Red Hat
  6. 2026-11-06 CVSS score added · Red Hat

References

  • TI-2026-46366 Server-side request forgery in mlflow KEVCVSS 3.1CRITICAL 9.3
  • TI-2023-03518 Absolute Path Traversal in mlflow/mlflow CVSS 3.1CRITICAL 10.0
  • TI-2023-01113 Path Traversal: '\..\filename' in mlflow/mlflow CVSS 3.1CRITICAL 9.8
  • TI-2025-31759 Redis Lua Use-After-Free may lead to remote code execution CVSS 3.1CRITICAL 10.0
  • TI-2026-81527 Code execution via scorer deserialization in MLflow servers CVSS 3.1CRITICAL 9.8
  • TI-2025-14028 Command Injection in mlflow/mlflow CVSS 3.1CRITICAL 10.0
See all 175 →

Sources