The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP). From 1.8.0 until 1.30.0 and 2.2.0, stateful Streamable HTTP servers, including FastMCP, MCPServer, Server.streamable_http_app(), and StreamableHTTPSessionManager, retain session entries without an idle expiration or aggregate session-count limit. DELETE, refused opening requests, and completed sessions do not reliably discard their entries, and each entry can retain parsed initialize parameters. A client that can reach the endpoint can therefore create ordinary short requests that grow server memory without bound until restart. Stateless HTTP, stdio, and SSE transports are not affected. This issue is fixed in versions 1.30.0 and 2.2.0.
CVE-2026-59951
“▲” beside the score: it is higher than the CVSS score beside it.
Score 7.5 from GitHub Security Advisory (severity: MODERATE) published 2026-10-15. A secondary CVSS source baseline 6.9; sources differ by 0.6.
Also known asEUVD-2026-101452 (ENISA EUVD) · GHSA-84m7-p3x7-pcfv (GitHub Security Advisories)Source: ENISA EUVD
- Lower severity and no public exploit yet
A fix is available — apply it.
- CVSS v3
- 6.9
- EG Score
- 7.5HIGHhigh confidence
- EG Risk
- 49EG Risk 49/100
EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.
How it’s computed (value × EchelonGraph’s weight)Severity75% × 45%Impact severity (EG Severity): CVSS 7.5 of 10. Never the KEV-floored or EPSS-lifted EG Score.Exploitation0.5% × 40%FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.Automatability100% × 15%CISA's SSVC Automatable value: yes (Vulnrichment).SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Attend at high (mission-essential systems).Exploitation none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.Action: A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high. - EPSS PROB
- 0.5%
- EPSS %ILE
- 39th
- KEV
- Not listed
What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)
The EG score (7.5): severity, escalated by confirmed exploitation. This CVE's 7.5 is its impact severity (EG Severity), not escalated.
- EG Severity
- 7.5 HIGHCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
- EG Likelihood
- 0.5% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-31). FIRST's exploitation probability, not an EchelonGraph model.
- Confirmed exploitation
- None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
- EG Priority
- SSVC Track at medium mission impactTrack at low or medium mission impact; Attend at high (mission-essential systems).CISA BOD 26-04: 14 days if the affected system is publicly exposed; 60 days if it is not.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.
SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Attend at high (mission-essential systems).
A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.
Exploitation none (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table
BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; 60 days if it is not.
The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it
Published
October 14, 2026
Last Modified
October 16, 2026
Advisory Details (7)
Auto-updated Oct 14, 2026Streamable HTTP sessions were never reclaimed by default and kept their initialize payloads · Advisory · modelcontextprotocol/python-sdk · GitHub
https://github.com/modelcontextprotocol/python-sdk/security/advisories/GHSA-84m7-p3x7-pcfvv2.2.0
Patch available: modelcontextprotocol/python-sdk v2.2.0
https://github.com/modelcontextprotocol/python-sdk/releases/tag/v2.2.0v1.30.0
Patch available: modelcontextprotocol/python-sdk v1.30.0
https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.30.0[v1.x] Expire idle Streamable HTTP sessions by default and cap concurrent sessions
Patch available: modelcontextprotocol/python-sdk v1.30.0 (PR #3426 merged 2026-09-02)
https://github.com/modelcontextprotocol/python-sdk/pull/3426Expire idle Streamable HTTP sessions by default and cap concurrent sessions
Patch available: modelcontextprotocol/python-sdk v2.2.0 (PR #3395 merged 2026-08-28)
https://github.com/modelcontextprotocol/python-sdk/pull/3395commit d2290ca34347 (modelcontextprotocol/python-sdk)
Patch available: modelcontextprotocol/python-sdk v2.2.0 (contains commit d2290ca34347)
https://github.com/modelcontextprotocol/python-sdk/commit/d2290ca3434731b68ea3e2270bc06a6e6575931bcommit 92120b4b0f50 (modelcontextprotocol/python-sdk)
Patch available: modelcontextprotocol/python-sdk v1.30.0 (contains commit 92120b4b0f50)
https://github.com/modelcontextprotocol/python-sdk/commit/92120b4b0f50385af096592d7cee932fc1d994e7Vendor Advisories for CVE-2026-59951(4)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
- RHSA-2026:92667Red Hat Product SecurityCritical
Red Hat Security Advisory: satellite/foreman-mcp-server-rhel9 container image available as a Technology Preview
- RHSA-2026:92666Red Hat Product SecurityCritical
Red Hat Security Advisory: satellite/foreman-mcp-server-rhel9 container image available as a Technology Preview
- RHSA-2026:92510Red Hat Product SecurityCritical
Red Hat Security Advisory: RHOAI 3.4.6 - Red Hat OpenShift AI
- GHSA-84m7-p3x7-pcfvGitHub Security AdvisoriesMedium
MCP Python SDK: Unbounded Session Accumulation in StreamableHTTP Transport Enables Resource Exhaustion
Patch Availability(2)
| Vendor / Ecosystem | Fix (by version range) / Patch | Released | Source |
|---|---|---|---|
| pip | mcp @ 1.30.0 (fixes >= 1.8.0, < 1.30.0) | — | ghsa |
| pip | mcp @ 2.2.0 (fixes >= 2.0.0, < 2.2.0) | — | ghsa |
Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.
Affected Packages
(1 across 1 ecosystem)
PyPI(1)
| Package | Vulnerable range | Fix by version range | Dependents |
|---|---|---|---|
| mcp | 1.10.0 ... 1.9.4 (43 versions) |
| — |
Weakness Classification(3)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 10× in last 7d / 29× in last 30d)
Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.
- 2026-11-01 16:35 UTCEPSS rescoreEPSS 0.5% · 39th percentile
- 2026-11-01 07:41 UTCGHSA enrichmentGHSA-84m7-p3x7-pcfv · GitHub severity MODERATE · GitHub CVSS 7.5
- 2026-11-01 07:41 UTCEG score recompute▲ 0.60
- 2026-10-31 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
- 2026-10-30 16:34 UTCEPSS rescoreEPSS 0.5% · 39th percentile
- 2026-10-29 16:39 UTCEG score recompute
- 2026-10-29 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
- 2026-10-28 16:32 UTCEPSS rescoreEPSS 0.5% · 39th percentile
- 2026-10-27 16:32 UTCEPSS rescoreEPSS 0.5% · 39th percentile
- 2026-10-26 16:31 UTCEPSS rescoreEPSS 0.5% · 39th percentile
- 2026-10-25 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
- 2026-10-25 14:16 UTCEG score recompute
- 2026-10-24 16:33 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-23 16:32 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-22 20:54 UTCEG score recompute
- 2026-10-22 16:34 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-21 16:33 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-19 16:32 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-18 16:32 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-18 03:26 UTCEG score recompute
- 2026-10-17 16:35 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-16 16:43 UTCEPSS rescoreEPSS 0.5% · 38th percentile
- 2026-10-15 16:37 UTCEG score recompute
- 2026-10-15 16:32 UTCEPSS rescoreEPSS 0.5% · 38th percentile
Show 4 moreShow fewer
- 2026-10-15 15:29 UTCEG score recompute
- 2026-10-14 18:31 UTCEG score recompute
- 2026-10-14 16:33 UTCEG score recomputeFirst assessed: 6.9 MEDIUM
- 2026-10-14 16:29 UTCMITRE cvelistV5first tracked
Related CVEs(same product + same CWE)
Same product
9 shownPyPI:mcp
Frequently asked(5)
What is CVE-2026-59951?
When was the CVE record for CVE-2026-59951 published?
Is CVE-2026-59951 actively exploited?
What is the CVSS score of CVE-2026-59951?
How do I remediate CVE-2026-59951?
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-59951
Is Your Infrastructure Affected by CVE-2026-59951?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.