Skip to main content
EPSS 0.4%top 69%

CVE-2026-52870: CWE-862: Missing Authorization in modelcontextprotocol python-sdk

0
High
Published: 08/13/2026 (08/13/2026, 17:24:19 UTC)
Source: CVE Database V5
Vendor/Project: modelcontextprotocol
Product: python-sdk

Description

### Summary In affected versions, the default request handlers installed by the experimental tasks feature (`server.experimental.enable_tasks()`) 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.enable_tasks()`. If `grep -r enable_tasks` 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.enable_tasks()` 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 `run_task()` 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.

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

modelcontextprotocol

python-sdk

Affected versions
>=1.23.0 <1.27.2
mcp
pkg:pypi/mcp
Affected versions
<1.27.2 >=1.23.0

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: 07/22/2026, 23:03:16 UTC

Technical Analysis

The MCP Python SDK (modelcontextprotocol) versions >=1.23.0 and <1.27.2 contain a missing authorization vulnerability (CWE-862) in default handlers installed by server.experimental.enable_tasks(). These handlers for tasks/list, tasks/get, tasks/result, and tasks/cancel operate solely on task identifiers without tracking the session that created each task. As a result, any connected client can access or manipulate tasks created by other clients. The vulnerability is addressed in version 1.27.2.

Potential Impact

An attacker with access to the MCP Python SDK server can enumerate other clients' tasks, read their results, consume their messages, or cancel their tasks. This leads to unauthorized disclosure of task data, partial integrity loss, and availability impact on other clients' tasks. The CVSS 3.1 base score is 7.6 (High), reflecting network attack vector, low attack complexity, required privileges, no user interaction, unchanged scope, high confidentiality impact, low integrity impact, and low availability impact.

Mitigation Recommendations

Upgrade to MCP Python SDK version 1.27.2 or later, where this missing authorization vulnerability is fixed. No other mitigation or temporary workaround is indicated in the available data.

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
2026-06-08T21:44:27.364Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6a57eb0d68715ace4363c934

Added to database: 07/15/2026, 20:18:21 UTC

Last enriched: 07/22/2026, 23:03:16 UTC

Last updated: 10/12/2026, 18:48:20 UTC

Views: 173

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