CVE-2026-59951: CWE-400: Uncontrolled Resource Consumption in modelcontextprotocol python-sdk
Description
CVE-2026-59951 is a medium severity vulnerability in the modelcontextprotocol Python SDK (mcp) affecting stateful Streamable HTTP servers. Versions from 1.8.0 up to but not including 1.30.0, and from 2.0.0 up to but not including 2.2.0, retain session entries without idle expiration or session-count limits. This causes uncontrolled memory growth as session entries are not reliably discarded, allowing a remote client to cause resource exhaustion. The issue is fixed in versions 1.30.0 and 2.2.0.
CVSS v4.0
Score 6.9medium
Affected software
modelcontextprotocol
python-sdk
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The MCP Python SDK implements the Model Context Protocol with stateful Streamable HTTP servers such as FastMCP and MCPServer. In affected versions, these servers retain session entries indefinitely without idle expiration or aggregate session-count limits. DELETE requests, refused openings, and completed sessions do not reliably remove their session entries, which retain parsed initialization parameters. This allows a remote client to send short requests that cause unbounded memory growth on the server until it is restarted. Stateless HTTP, stdio, and SSE transports are not affected. The vulnerability is addressed in versions 1.30.0 and 2.2.0.
Potential Impact
An unauthenticated remote attacker can cause uncontrolled resource consumption (memory exhaustion) on affected servers by sending ordinary short requests, leading to potential denial of service until the server is restarted. There is no indication of privilege escalation or data compromise. The impact is limited to availability degradation due to memory exhaustion.
Mitigation Recommendations
Upgrade to modelcontextprotocol python-sdk versions 1.30.0 or later, or 2.2.0 or later, where this issue is fixed. There is no indication of alternative mitigations or temporary workarounds. Patch status is confirmed fixed in these versions.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-07-07T18:49:15.607Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6acfaf362cdf04f65694d3b1
Added to database: 10/14/2026, 16:35:02 UTC
Last enriched: 10/14/2026, 16:48:56 UTC
Last updated: 10/14/2026, 19:00:32 UTC
Views: 13
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.