Skip to main content

Snyk agent scan: MCP Python SDK: Experimental task handlers allow any client to access and cancel other clients' tasks (CVE-2026-52870)

0
High
Published: 08/13/2026 (08/13/2026, 17:35:48 UTC)
Source: GCVE Database
Product: snyk-agent-scan

Description

The MCP Python SDK's experimental task handlers feature, when enabled, does not verify session ownership of tasks. This allows any connected client to list, read results from, and cancel tasks created by other clients on the same server. The vulnerability affects servers that enable the experimental tasks feature and use default handlers without session validation. It is fixed in version 1.27.2 and later, which embed session markers in task IDs and restrict task access to the owning session.

CVSS v3.1

Score 7.6high

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

Affected software

Homebrewmore threats →ghsa
snyk-agent-scan
pkg:brew/snyk-agent-scan
Affected versions
>=0.4.3 <0.5.17

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: 10/22/2026, 17:28:44 UTC

Technical Analysis

In affected versions of the MCP Python SDK (>=0.4.3 <0.5.17), the default request handlers installed by the experimental tasks feature (`server.experimental.enable_tasks()`) do not check which client session created a task before allowing operations on it. This means that on servers with multiple connected clients, any client can enumerate all tasks, read their statuses and results, consume queued messages intended for other clients, and cancel tasks belonging to others. The vulnerability arises because the handlers operate solely on task identifiers without tracking session ownership. The issue is mitigated in version 1.27.2 and later by embedding an opaque per-session marker in task IDs and restricting handlers to only allow access to tasks belonging to the requesting session. Alternatively, disabling the experimental tasks feature or implementing custom handlers that validate session ownership also mitigates the risk.

Potential Impact

Clients connected to a server running an affected version with the experimental tasks feature enabled can access and interfere with tasks created by other clients. This includes reading sensitive task results and elicitation payloads, consuming messages meant for other clients, and cancelling their tasks. This compromises confidentiality and availability of task data between clients sharing the same server instance. Servers not enabling the experimental feature or using custom handlers that enforce session validation are not affected.

Mitigation Recommendations

A fix is available in version 1.27.2 or later, which adds session ownership validation by embedding a per-session marker in task IDs and restricting default handlers to only operate on tasks belonging to the requesting session. Servers should upgrade to this version to remediate the vulnerability. Alternatively, keep the experimental tasks feature disabled or implement custom task handlers that validate session ownership before acting on tasks. No other mitigation is required if the feature is not enabled.

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

Technical Details

Gcve Source
db.gcve.eu
Osv Id
BREW-snyk-agent-scan-CVE-2026-52870
Osv Schema Version
1.7.3
Ecosystems
["Homebrew"]
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6ada44e64d27ba8daa6a52b2

Added to database: 10/22/2026, 17:16:22 UTC

Last enriched: 10/22/2026, 17:28:44 UTC

Last updated: 10/22/2026, 17:28:44 UTC

Views: 2

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