CVSS 3.1
5.9 mediumCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:NMedium (5.9) 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:N/UI:N/S:U/C:H/I:N/A:Nmcp (PyPI): fixed in 2.2.0, 1.30.0Explain CVE-2026-116685 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-116685?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-116685?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-2026-116685 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 | >= 1.8.0, < 1.30.0 |
| modelcontextprotocol python-sdk | >= 2.0.0, < 2.2.0 |
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-5h93-6whr-6q8j | PyPI | mcp | >=2.0.0 <2.2.0 | 2.2.0 |
| GHSA-5h93-6whr-6q8j | PyPI | mcp | >=1.8.0 <1.30.0 | 1.30.0 |
Red Hat rates this Moderate.
This vulnerability is rated as having a Moderate severity for Red Hat products because successful exploitation requires an adversary to manipulate or compromise the redirect responses of a trusted endpoint, representing a complex attack scenario. Within Red Hat environments utilizing Model Context Protocol client integrations over HTTP or SSE transports, exposure is limited to custom headers and request payloads, whereas standard authorization bearer tokens are discarded on cross-origin redirects. Deployments utilizing stdio-based MCP communications, as well as standalone MCP server implementations, remain unaffected by this flaw.
| 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-2026-116685.
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-200 (59).