VulnerabilityPublished 13 Aug 2026Updated 29 Oct 2026

CVE-2026-52870: MCP Python SDK · Experimental task handlers allow any client to access and cancel other clients' tasks

Affects mistral-vibeSource GCVE Database

Compare

Authoritative record:CVE-2026-52870· High 7.6

Not known to be exploited · CVSS 7.6 High : upgrade to 2.17.0 soon.

Data as of 30 Oct 2026, 08:01 UTC

CVSS 3.1 base score

7.6High

How severe the flaw is on the 0–10 CVSS scale.

Patch: Available – fixed in 2.17.0

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L

Attack Vector: Network
Attack Complexity: Low
Privileges Required: Low
User Interaction: None
Scope: Unchanged
Confidentiality: High
Integrity: Low
Availability: Low

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: Low: The attacker is authorized with (i.e., requires) privileges that provide basic user capabilities that could normally affect only settings and files owned by a user. Alternatively, an attacker with Low privileges may have the ability to cause an impact only to non-sensitive resources.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on the impacted component.
Availability: Low: Performance is reduced or there are interruptions in resource availability. Even if repeated exploitation of the vulnerability is possible, the attacker does not have the ability to completely deny service to legitimate users. The resources in the impacted component are either partially available all of the time, or fully available only some of the time, but overall there is no direct, serious consequence to the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 15 Jul 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 29 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade mistral-vibe to 2.17.0.

Affected software

Product	Affected	Fixed in
Homebrewmistral-vibe`pkg:brew/mistral-vibe`Other threats	Affected >=1.1.1 <2.17.0	Fixed in 2.17.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Upgrade to MCP Python SDK version 2.17.0 or later, which embeds a per-session marker in task IDs and restricts default handlers to only operate on tasks owned by the requesting session. Alternatively, disable the experimental tasks feature (do not call server.experimental.enable_tasks()) or implement custom task handlers that validate session ownership before acting on tasks. These mitigations prevent unauthorized access and manipulation of tasks across client sessions.

Description

The MCP Python SDK's experimental task handlers feature, when enabled via server.experimental.enable_tasks(), does not verify task ownership by client session. This allows any connected client to list, read results from, and cancel tasks created by other clients on the same server. The issue affects versions from 1.1.1 up to but not including 2.17.0. The vulnerability is fixed in version 2.17.0 by embedding a per-session marker in task IDs and restricting handlers to operate only on tasks belonging to the requesting session.

Impact

Clients connected to a server running an affected MCP Python SDK version with the experimental tasks feature enabled can access and manipulate tasks belonging to other clients. This includes reading sensitive task results and elicitation payloads, consuming messages intended for other clients, and cancelling their tasks. This compromises confidentiality and availability of task data across client sessions. Servers not enabling the experimental tasks feature or using custom handlers that enforce session validation are not affected.

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 30 Oct 2026, 08:01 UTC

Technical details

References

Community reviews

Related threats