CVE-2026-52870: MCP Python SDK: Experimental task handlers allow any client to access and cancel other clients' tasks
Summary In affected versions, the default request handlers installed by the experimental tasks feature (server.experimental.enabletasks()) did not check which session created a task before acting on it. On a server with more than one connected client, any client could observe, read results from, and cancel tasks belonging to other clients.
Am I affected? Only if the developer's application server calls server.experimental.enabletasks(). If grep -r enabletasks over their codebase finds nothing, the application is not affected.
Details When tasks support is enabled on the low-level server, default handlers are registered for tasks/list, tasks/get, tasks/result, and tasks/cancel. These handlers operated on the task identifier alone and kept no record of the session that created each task. Because tasks/list returned every task in the store, a connected client did not need to know any identifiers in advance: it could enumerate all tasks, read any task's status and result via tasks/get and tasks/result, retrieve queued task messages — such as elicitation requests intended for the task's creator, which are removed from the queue on delivery, so the intended recipient never receives them — and cancel any task via tasks/cancel.
Impact Servers that call server.experimental.enabletasks() and serve multiple clients are affected: one client can read other clients' task results and elicitation payloads, consume messages meant for them, and cancel their tasks. The feature is experimental and opt-in, so servers that never enable it are unaffected. Servers that registered their own task handlers instead of the defaults are affected only if those handlers have the same omission.
Mitigation Upgrade to version 1.27.2 or later, in which task IDs generated by runtask() embed an opaque per-session marker and the default handlers restrict each session to its own tasks: requests for another session's task receive "task not found", and tasks/list returns only the requesting session's tasks. Tasks created with explicitly chosen IDs or written directly through a TaskStore remain reachable by ID but are not listed. Alternatively, leave the experimental tasks feature disabled, or register task handlers that validate session ownership.
Other sources
The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP). From 1.23.0 until 1.27.2, default handlers installed by server.experimental.enabletasks() for tasks/list, tasks/get, tasks/result, and tasks/cancel operate only on task identifiers without recording the session that created each task, allowing any connected client to enumerate, read results from, consume messages for, or cancel other clients' tasks. This issue is fixed in version 1.27.2.
— NVD
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
pip/mcpto a version that resolves this vulnerability.Fixed in 1.27.2 - Upgrade
Upgrade
MCP Python SDK (mcp on PyPI)to a version that resolves this vulnerability.Fixed in 1.27.2 - Configuration
Do not call server.experimental.enable_tasks(); if you must use it, only do so when you need multi-client access, otherwise leave experimental task handlers disabled.
MCP Python SDK (mcp) experimental tasks feature server.experimental.enable_tasks() = disabled
Event History
Frequently Asked Questions
What is the severity of CVE-2026-52870?
CVE-2026-52870 has a high severity rating of 7.6.
How do I fix CVE-2026-52870?
You can fix CVE-2026-52870 by upgrading to a version of the MCP Python SDK later than 1.27.2.
What types of tasks are affected by CVE-2026-52870?
CVE-2026-52870 affects the experimental task handlers for tasks/list, tasks/get, tasks/result, and tasks/cancel.
Who is impacted by CVE-2026-52870?
Any client using the MCP Python SDK versions 1.23.0 to 1.27.2 is vulnerable to CVE-2026-52870.
What happens if I don't address CVE-2026-52870?
If not addressed, CVE-2026-52870 allows unauthorized clients to access and cancel other clients' tasks, leading to potential data exposure or disruption.