CVSS 4.0
6.9 mediumCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:NMedium (6.9) in modelcontextprotocol python-sdk. EPSS 0.5% estimated probability of exploitation activity in the next 30 days. Fixed in mcp 1.30.0, 2.2.0.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:Nmcp (PyPI): fixed in 1.30.0, 2.2.0Explain CVE-2026-59951 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-59951?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-59951?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-2026-59951 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-84m7-p3x7-pcfv | PyPI | mcp | >=1.8.0 <1.30.0 | 1.30.0 |
| GHSA-84m7-p3x7-pcfv | PyPI | mcp | >=2.0.0 <2.2.0 | 2.2.0 |
| Distribution | Release | Package | Fixed in | Advisory |
|---|---|---|---|---|
| openSUSE | Tumbleweed | headroom | 0.42.0-1.1 | openSUSE-SU-2026:12484-1 |
| openSUSE | Tumbleweed | python-mcp | 1.30.0-1.1 | openSUSE-SU-2026:12475-1 |
From the distributions' data via OSV.dev: SUSE security data, CC BY 4.0. Modified: reformatted and linked to CVE records. Credits. On the distributions' own pages: openSUSE.
Red Hat rates this Important.
Red Hat Product Security rates this vulnerability as Important because unauthenticated remote attackers can exhaust host memory and cause an application-level denial of service without requiring user interaction or specialized privileges. Within Red Hat AI, Lightspeed, and automation offerings that incorporate Model Context Protocol (MCP) services, exposure occurs when servers are configured to listen on network-accessible, stateful Streamable HTTP endpoints. Deployments operating with stateless HTTP configurations, standard I/O (stdio), or Server-Sent Events (SSE) transports are not vulnerable to this session buildup.
| Product | Package | State | Advisory |
|---|---|---|---|
| Red Hat AI Inference Server 3.5 | rhaii/vllm-cpu-rhel9:1793444554 | Fixed 2026-11-03 | RHSA-2026:94702 |
| Red Hat AI Inference Server 3.5 | rhaii/vllm-rocm-rhel9:1793444456 | Fixed 2026-11-03 | RHSA-2026:94709 |
| Red Hat AI Inference Server 3.5 | rhaii/vllm-spyre-rhel9:1793444409 | Fixed 2026-11-03 | RHSA-2026:94717 |
| Red Hat AI Inference Server 3.5 | rhaii/vllm-gaudi-rhel9:1793444510 | Fixed 2026-11-03 | RHSA-2026:94721 |
| Red Hat AI Inference Server 3.5 | rhaii/vllm-cuda-rhel9:1793444600 | Fixed 2026-11-03 | RHSA-2026:94738 |
| Red Hat OpenShift AI 3.4 | rhoai/odh-kserve-router-rhel9:1792688864 | Fixed 2026-10-29 | RHSA-2026:92510 |
| Red Hat Satellite 6.18 | satellite/foreman-mcp-server-rhel9:1793272276 | Fixed 2026-10-29 | RHSA-2026:92667 |
| Red Hat Satellite 6.19 | satellite/foreman-mcp-server-rhel9:1793272279 | Fixed 2026-10-29 | RHSA-2026:92666 |
| Ansible Automation Orchestrator 2026 | ansible-automation-platform/automation-orchestrator-backend-rhel9 | Affected | |
| Exploit Intelligence | exploit-intelligence/vulnerability-analysis-rhel9 | Affected | |
| Lightspeed Core | lightspeed-core/lightspeed-stack-rhel9 | Affected | |
| Lightspeed Core | lightspeed-core/rag-tool-cpu-rhel9 | Affected | |
| Lightspeed Core | lightspeed-core/rag-tool-cuda-12.9-rhel9 | Affected | |
| Migration Toolkit for Applications 8 | mta/mta-solution-server-rhel9 | Affected | |
| OpenShift Lightspeed | openshift-lightspeed/lightspeed-agentic-sandbox-rhel9 | Affected | |
| OpenShift Lightspeed | openshift-lightspeed/lightspeed-service-api-rhel9 | Affected | |
| Red Hat AI Inference Server | rhaiis/vllm-cpu-rhel9 | Not affected | |
| Red Hat AI Inference Server | rhaiis/vllm-cuda-rhel9 | Not affected | |
| Red Hat AI Inference Server | rhaiis/vllm-rocm-rhel9 | Not affected | |
| Red Hat AI Inference Server | rhaiis/vllm-tpu-rhel9 | Not affected | |
| 27 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-2026-59951.
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.