PatchSiren cyber security CVE debrief
CVE-2026-52870 modelcontextprotocol CVE debrief
The MCP Python SDK, called mcp on PyPI, has a high-severity vulnerability tracked as CVE-2026-52870. From version 1.23.0 until 1.27.2, default handlers installed by server.experimental.enable_tasks() for tasks/list, tasks/get, tasks/result, and tasks/cancel operate only on task identifiers without recording the session that created each task. This allows any connected client to enumerate, read results from, consume messages for, or cancel other clients' tasks. The issue is fixed in version 1.27.2.
- Vendor
- modelcontextprotocol
- Product
- python-sdk
- CVSS
- HIGH 7.6
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-07-15
- Original CVE updated
- 2026-07-17
- Advisory published
- 2026-07-15
- Advisory updated
- 2026-07-17
Who should care
Users of the MCP Python SDK, particularly those who have installed the mcp package from PyPI and are using versions between 1.23.0 and 1.27.2, should be aware of this vulnerability and take immediate action to upgrade to version 1.27.2 or later.
Technical summary
The MCP Python SDK's server.experimental.enable_tasks() function installs default handlers for tasks/list, tasks/get, tasks/result, and tasks/cancel. However, these handlers only operate on task identifiers and do not record the session that created each task. This oversight allows any connected client to enumerate, read results from, consume messages for, or cancel tasks created by other clients. The vulnerability has a CVSS score of 7.6 and is classified as HIGH severity.
Defensive priority
High priority should be given to upgrading the MCP Python SDK to version 1.27.2 or later. In the meantime, users can consider implementing compensating controls, such as monitoring for suspicious task-related activity or restricting access to task management functions.
Recommended defensive actions
- Upgrade to MCP Python SDK version 1.27.2 or later
- Review and restrict access to task management functions
- Monitor for suspicious task-related activity
- Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up
- Review the supplied official advisory or CVE record to validate affected scope, severity, and vendor guidance
- Plan vendor-supported updates or mitigations through normal change control where exposure is confirmed
- Check relevant monitoring, detection, and logs for exposed assets that need extra review
Evidence notes
The CVE record was published on 2026-07-15T20:17:38.577Z and was last modified on 2026-07-16T14:16:53.680Z. The NVD entry is currently Undergoing Analysis. The vulnerability was fixed in version 1.27.2 of the MCP Python SDK.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-52870 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-52870
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-52870 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-52870
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
Source reference
Unverified legacy reference
URL: https://github.com/modelcontextprotocol/python-sdk/commit/62137874ff26dd74d2fea80ff528a7fd9ca7a5e7
-
Source reference
Unverified legacy reference
URL: https://github.com/modelcontextprotocol/python-sdk/pull/2720
-
Source reference
Unverified legacy reference
URL: https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.27.2
-
Source reference
Unverified legacy reference
URL: https://github.com/modelcontextprotocol/python-sdk/security/advisories/GHSA-hvrp-rf83-w775
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.