CVSS 3.1
6.8 mediumCVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:NMedium (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.
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:Nmcp (PyPI): fixed in 2.2.0, 1.30.0Explain 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.
From the CNA's record in the CVE List.
| Product | Affected |
|---|---|
| modelcontextprotocol python-sdk | >= 1.10.0, < 1.30.0 |
| modelcontextprotocol python-sdk | >= 2.0.0, < 2.2.0 |
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-w4fh-qvv9-3v23 | PyPI | mcp | >=2.0.0 <2.2.0 | 2.2.0 |
| GHSA-w4fh-qvv9-3v23 | PyPI | mcp | >=1.10.0 <1.30.0 | 1.30.0 |
Red Hat rates this Moderate.
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.
| Product | Package | State | Advisory |
|---|---|---|---|
| Ansible Automation Orchestrator 2026 | ansible-automation-platform/automation-orchestrator-backend-rhel9 | Fix deferred | |
| Exploit Intelligence | exploit-intelligence/vulnerability-analysis-rhel9 | Out of support scope | |
| Lightspeed Core | lightspeed-core/lightspeed-stack-rhel9 | Fix deferred | |
| Lightspeed Core | lightspeed-core/rag-tool-cpu-rhel9 | Fix deferred | |
| Lightspeed Core | lightspeed-core/rag-tool-cuda-12.9-rhel9 | Fix deferred | |
| Migration Toolkit for Applications 8 | mta/mta-solution-server-rhel9 | Fix deferred | |
| OpenShift Lightspeed | openshift-lightspeed/lightspeed-agentic-sandbox-rhel9 | Fix deferred | |
| OpenShift Lightspeed | openshift-lightspeed/lightspeed-service-api-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii-fast/vllm-cpu-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii-fast/vllm-cuda-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii-fast/vllm-gaudi-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii-fast/vllm-neuron-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii-fast/vllm-omni-cuda-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii-fast/vllm-rocm-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii-fast/vllm-spyre-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii-fast/vllm-tpu-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-cpu-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-cuda-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-gaudi-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-neuron-rhel9 | Fix 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.