cve.bz

CVE-2026-116684 modelcontextprotocol python-sdk: Incorrect Authorization

6.8 mediumEPSS 0.4%Fix available

Medium (6.8) in modelcontextprotocol python-sdk. EPSS 0.4% estimated probability of exploitation activity in the next 30 days. Fixed in mcp 1.30.0, 2.2.0.

On this page
The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.10.0 until 1.30.0 and 2.2.0, server-side bearer authentication configured through AuthSettings with token_verifier accepts a valid token issued for another service when the authorization server serves multiple resources and the TokenVerifier does not independently validate the aud audience. This resource-confusion flaw lets a token holder authenticate to the wrong MCP server and exercise that token's resulting access. This issue is fixed in versions 1.30.0 and 2.2.0.

Severity

CVSS 3.1

6.8 medium
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:N
EPSS
0.4% (unchanged from 0.4% a week ago) estimated probability of exploitation activity in the next 30 days; 31st percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CWE
CWE-863 Incorrect Authorization
OWASP Top 10
A01:2025 Broken Access Control
Published
Modified
NVD analysis
Awaiting analysis
Record from
the NVD, synced

Fix and patched versions

  • mcp (PyPI): fixed in 2.2.0, 1.30.0

Ask an AI about this CVE

Show the promptExplain CVE-2026-116684 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-116684?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-116684?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-116684 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
modelcontextprotocol python-sdk>= 1.10.0, < 1.30.0
modelcontextprotocol python-sdk>= 2.0.0, < 2.2.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-w4fh-qvv9-3v23PyPImcp>=2.0.0 <2.2.02.2.0
GHSA-w4fh-qvv9-3v23PyPImcp>=1.10.0 <1.30.01.30.0

Red Hat

Red Hat rates this Moderate.

Red Hat's statement

Red Hat has rated this vulnerability as Moderate impact because an attacker must already possess valid credentials from a shared identity provider, and exploitation depends on a multi-service authentication topology where distinct endpoints accept tokens from the same issuer. In typical Red Hat deployments where Model Context Protocol endpoints are integrated into artificial intelligence workflows or platform services, exposure is limited to environments where single authorization servers issue generic tokens across disparate application resources. While successful exploitation permits unauthorized service interactions under the context of the supplied credential, it does not provide privilege escalation within the underlying host or container infrastructure.

ProductPackageStateAdvisory
Ansible Automation Orchestrator 2026ansible-automation-platform/automation-orchestrator-backend-rhel9Fix deferred
Exploit Intelligenceexploit-intelligence/vulnerability-analysis-rhel9Out of support scope
Lightspeed Corelightspeed-core/lightspeed-stack-rhel9Fix deferred
Lightspeed Corelightspeed-core/rag-tool-cpu-rhel9Fix deferred
Lightspeed Corelightspeed-core/rag-tool-cuda-12.9-rhel9Fix deferred
Migration Toolkit for Applications 8mta/mta-solution-server-rhel9Fix deferred
OpenShift Lightspeedopenshift-lightspeed/lightspeed-agentic-sandbox-rhel9Fix deferred
OpenShift Lightspeedopenshift-lightspeed/lightspeed-service-api-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-cpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-gaudi-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-neuron-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-omni-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-rocm-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-spyre-rhel9Fix deferred
Red Hat AI Inference Serverrhaii-fast/vllm-tpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-cpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-gaudi-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-neuron-rhel9Fix deferred
30 more in the JSON and on Red Hat's page.

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-116684.

References

Check your stackJSON