Skip to main content

CVE-2026-109527: CWE-770: Allocation of Resources Without Limits or Throttling in modelcontextprotocol python-sdk

0
High
VulnerabilityCVE-2026-109527cvecve-2026-109527cwe-770
Published: 10/14/2026 (10/14/2026, 17:52:35 UTC)
Source: CVE Database V5
Vendor/Project: modelcontextprotocol
Product: python-sdk

Description

CVE-2026-109527 affects the Model Context Protocol Python SDK in versions before 1.29.1 and from 2.0.0a1 up to but not including 2.1.0. The vulnerability involves the Streamable HTTP session manager, SSE message endpoint, and OAuth authorization-server routes buffering complete HTTP request bodies without enforcing size limits. This allows an unauthenticated remote attacker to send large request bodies that consume excessive memory, potentially exhausting server memory or causing server termination. Deployments with upstream request-size limits or using stdio-only servers are not affected. The issue is fixed in versions 1.29.1 and 2.1.0.

CVSS v3.1

Score 7.5high

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected software

modelcontextprotocol

python-sdk

Affected versions
<1.29.1>=2.0.0a1 <2.1.0
modelcontextprotocol-python-sdk
pkg:pypi/modelcontextprotocol-python-sdk
Affected versions
<1.29.1>=2.0.0a1 <2.1.0

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

AILast updated: 10/14/2026, 18:18:32 UTC

Technical Analysis

The Model Context Protocol Python SDK versions prior to 1.29.1 and from 2.0.0a1 through 2.0.1 have a resource exhaustion vulnerability (CWE-770) due to lack of limits on buffered HTTP request body sizes in certain components (Streamable HTTP session manager, SSE message endpoint, OAuth authorization-server routes). An unauthenticated remote client can exploit this by sending large request bodies that consume multiple times their size in process memory, leading to repeated memory exhaustion or server termination. The vulnerability does not affect stdio-only servers or deployments with effective upstream request-size limits. Applications using StreamableHTTPServerTransport directly must enforce their own limits. The vulnerability is resolved in versions 1.29.1 and 2.1.0 of the SDK.

Potential Impact

An unauthenticated remote attacker can cause a denial of service by exhausting server memory or terminating the server process through sending large HTTP request bodies to affected endpoints. There is no impact on confidentiality or integrity. The attack requires network access to the vulnerable endpoints.

Mitigation Recommendations

Upgrade to Model Context Protocol Python SDK version 1.29.1 or later, or 2.1.0 or later, where the vulnerability is fixed. Deployments using stdio-only servers or with effective upstream request-size limits are not affected. Applications using StreamableHTTPServerTransport directly should implement their own request size limits to mitigate this issue.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-10-12T19:11:21.789Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6acfc4752cdf04f6569de054

Added to database: 10/14/2026, 18:05:41 UTC

Last enriched: 10/14/2026, 18:18:32 UTC

Last updated: 10/14/2026, 19:00:29 UTC

Views: 8

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

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

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses