PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-109527 modelcontextprotocol CVE debrief

CVE-2026-109527 debrief: The Model Context Protocol Python SDK is vulnerable to memory exhaustion through unbounded request bodies in versions before 1.29.1 and from 2.0.0a1 through 2.1.0. This vulnerability allows an unauthenticated remote client to send large declared or streamed request bodies, potentially exhausting memory or terminating the server. Defenders should assess exposure, particularly in deployments using Streamable HTTP session manager, SSE message endpoint, and OAuth authorization-server routes, and apply patches to prevent potential memory exhaustion attacks.

Vendor
modelcontextprotocol
Product
python-sdk
CVSS
HIGH 7.5
CISA KEV
Not listed in stored evidence
Original CVE published
2026-10-14
Original CVE updated
2026-10-14
Advisory published
2026-10-14
Advisory updated
2026-10-14

Who should care

Defenders responsible for Model Context Protocol Python SDK deployments, particularly those using Streamable HTTP session manager, SSE message endpoint, and OAuth authorization-server routes, should assess exposure and apply patches to prevent potential memory exhaustion attacks.

Why it matters

CVE-2026-109527 allows memory exhaustion through unbounded request bodies in Model Context Protocol Python SDK, impacting deployments using Streamable HTTP session manager, SSE message endpoint, and OAuth authorization-server routes. Defenders should verify exposure, apply patches, and implement request size limits to prevent potential DoS attacks.

  • Potential memory exhaustion leading to server termination
  • Increased risk of denial-of-service (DoS) attacks
  • Need for verification of affected versions and deployments
  • Priority for applying patches or implementing compensating controls

Technical summary

The Model Context Protocol Python SDK is vulnerable to memory exhaustion through unbounded request bodies in versions before 1.29.1 and from 2.0.0a1 through 2.1.0. An unauthenticated remote client can send large declared or streamed request bodies to consume multiple times the body size in process memory, potentially exhausting memory or terminating the server. Defenders should prioritize verifying exposure and applying patches for affected versions. Implementing request size limits for Streamable HTTP session manager, SSE message endpoint, and OAuth authorization-server routes can help prevent potential DoS attacks.

Defensive priority

Defenders should prioritize verifying exposure and applying patches for Model Context Protocol Python SDK versions before 1.29.1 and from 2.0.0a1 through 2.1.0.

Recommended defensive actions

  • Verify exposure of Model Context Protocol Python SDK deployments to unbounded request body attacks
  • Apply patches for affected versions (before 1.29.1 and from 2.0.0a1 through 2.1.0)
  • Implement request size limits for Streamable HTTP session manager, SSE message endpoint, and OAuth authorization-server routes
  • Monitor for large declared or streamed request bodies that could exhaust memory
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented

Evidence notes

The CVE record and source item provide details on the vulnerability. Additional verification is needed to confirm affected versions and deployments. Defenders should verify exposure by checking for unbounded request body attacks, review vendor guidance, and implement request size limits for Streamable HTTP session manager, SSE message endpoint, and OAuth authorization-server routes. Evidence limits suggest that further review of server configurations and request body sizes is necessary.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-109527 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-109527

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-109527 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-109527

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

  • Model Context Protocol Python SDK HTTP and OAuth endpoints allow memory exhaustion through unbou

    Unverified legacy reference

    URL: https://raw.githubusercontent.com/CVEProject/cvelistV5/main/cves/2026/109xxx/CVE-2026-109527.json

    cve_program_cvelist_v5

  • Source reference

    Unverified legacy reference

    URL: https://github.com/modelcontextprotocol/python-sdk/security/advisories/GHSA-fmmv-w9g8-j3gc

    Supplemental source - x_refsource_CONFIRM

  • Source reference

    Unverified legacy reference

    URL: https://github.com/modelcontextprotocol/python-sdk/commit/03aaebd3aadb2567878dd811cb1f141454e8a080

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/modelcontextprotocol/python-sdk/commit/4dc224fab201bdef2fd5a065976b7ca31420187c

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/modelcontextprotocol/python-sdk/commit/57394b0548d1e2dc2dce8d67d84985769df3b8bb

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/modelcontextprotocol/python-sdk/commit/5f0b6af9f2b0aad3be3ba5cbfe80a9e4ea32e189

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.29.1

    Supplemental source - x_refsource_MISC

  • Source reference

    Unverified legacy reference

    URL: https://github.com/modelcontextprotocol/python-sdk/releases/tag/v2.1.0

    Supplemental source - x_refsource_MISC

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.