CVE-2026-116686VulnerabilityPublished 27 Oct 2026

mcp · Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output

Affects mcpSource GCVE Database

Authoritative record:CVE-2026-116686· Medium 6.5

Not known to be exploited · CVSS 6.5 Medium : upgrade to 2.2.0 when convenient.

Data as of 27 Oct 2026, 22:27 UTC

CVSS 3.1 base score

6.5Medium

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

Patch: Available – fixed in 2.2.0, 1.30.0

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

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

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: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: Required: Successful exploitation of this vulnerability requires a user to take some action before the vulnerability can be exploited.
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: None: There is no loss of confidentiality within the impacted component.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: High: There is total loss of availability, resulting in the attacker being able to fully deny access to resources in the impacted component; this loss is either sustained (while the attacker continues to deliver the attack) or persistent (the condition persists even after the attack has completed). Alternatively, the attacker has the ability to deny some availability, but the loss of availability presents a direct, serious consequence to the impacted component (e.g., the attacker cannot disrupt existing connections, but can prevent new connections; the attacker can repeatedly exploit a vulnerability that, in each instance of a successful attack, leaks a only small amount of memory, but after repeated exploitation causes a service to become completely unavailable).

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 27 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: 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 26 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.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, 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 mcp to 2.2.0; mcp to 1.30.0.

Affected software

Product	Affected	Fixed in
PyPImcp	Affected >=2.0.0 <2.2.0	Fixed in 2.2.0
PyPImcp	Affected >=1.10.0 <1.30.0	Fixed in 1.30.0

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

AI-suggested

Upgrade the MCP Python SDK to version 1.30.0 (1.x) or 2.2.0 (2.x) or later, where the client no longer performs network or file access during schema validation. Until upgrading, only call tools on servers you fully trust. As a partial workaround, avoid calling tools whose outputSchema contains an $id or any $ref/$dynamicRef that does not start with '#'.

Description

The Model Context Protocol (MCP) Python SDK versions 1.10.0 through 1.29.1 and 2.0.0 through 2.1.1 contain a vulnerability where the client fetches server-chosen $ref URLs during tool result validation. This allows a malicious server to cause the client to make network or local file requests synchronously without timeout, potentially freezing the client session. The issue is fixed in versions 1.30.0 and 2.2.0.

Impact

The vulnerability allows a malicious MCP server to cause the client to synchronously fetch arbitrary URLs or local files from the client's network position during tool result validation. This can lead to denial of service by freezing the client session if the external resource is slow or unresponsive. There is no direct confidentiality or integrity impact reported. The CVSS v3.1 score is 6.5 (medium severity) with an impact primarily on availability.

Summary

In affected MCP Python SDK versions, when a connected MCP server declares an outputSchema for a tool, the SDK client validates each call_tool result using jsonschema's default resolver. This resolver fetches any $ref it cannot resolve locally by opening the referenced URL, which can be an http://, https://, or file:// URL. Consequently, a malicious server can cause the client to synchronously fetch arbitrary URLs or local files on every tool call, potentially stalling the client indefinitely if the target connection hangs. This vulnerability affects clients using ClientSession, ClientSessionGroup, or the 2.x Client classes when calling tools on untrusted servers. The issue is resolved in MCP SDK versions 1.30.0 and 2.2.0 by restricting reference resolution to within the schema document and standard metaschemas only, preventing external network or file access during validation.

CWE-918Server-Side Request Forgery (SSRF) (opens in a new tab)
Base weaknessCWE Top 25 (2025): #22OWASP Top 10 A01:2025: Broken Access Control (opens in a new tab)
The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.
OWASP Cheat Sheets
Server Side Request Forgery Prevention (opens in a new tab)
Unvalidated Redirects and Forwards (opens in a new tab)
Cross Site Scripting Prevention (opens in a new tab)
DOM based XSS Prevention (opens in a new tab)
Authorization (opens in a new tab)
OWASP ASVS 4.0.3
V12.6.1 (opens in a new tab)
V5.2.6 (opens in a new tab)
Attack patterns
Server Side Request Forgery (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 27 Oct 2026, 22:27 UTC

WeaknessesCWE-918

Technical details

References

Community reviews

Related threats