CVE-2026-116686VulnerabilityPublished 29 Oct 2026

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

Affects omnaraSource GCVE Database

Compare

Authoritative record:CVE-2026-116686· Medium 6.5

Not known to be exploited · CVSS 6.5 Medium · fixed in 1.30.0 : update omnara when convenient.

Data as of 30 Oct 2026, 08:46 UTC

CVSS 3.1 base score

6.5Medium

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

Thin evidence

One scorer or none

CVSS scores by source
CNA (GitHub_M)	CVSS 3.1	6.5

Patch: Available – fixed in 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
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

Affected software

Product	Affected	Fixed in
Homebrewomnara`pkg:brew/omnara`Other threats	Affected >=1.5.2	Fixed in–

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 client to version 1.30.0 or later for the 1.x series, or 2.2.0 or later for the 2.x series, where the vulnerability is fixed by restricting schema reference resolution to internal document references only. Until an upgrade is possible, only call tools on fully trusted MCP servers. As a partial mitigation, 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 client versions 1.10.0 through 1.29.1 and 2.0.0 through 2.1.1 validate tool output schemas by fetching external $ref URLs, including http, https, and file URLs, from the client's network position. This can cause the client to make unintended network or local file requests and stall if the remote endpoint is unresponsive. The issue affects clients calling tools on servers they do not fully control.

Impact

An attacker controlling or influencing the MCP server can cause the client to perform unintended network requests or local file reads from the client's environment, potentially exposing internal network resources or sensitive local files. Furthermore, the synchronous fetch without timeout can cause the client application to stall indefinitely, resulting in denial of service for the affected session or process. There is no direct confidentiality or integrity impact reported, but availability is impacted due to stalling.

Summary

In affected MCP Python SDK client versions, when a connected MCP server declares an outputSchema for a tool, the 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 may be an http, https, or file URL. Consequently, a malicious or compromised server can cause the client to fetch arbitrary URLs or local files from the client's network environment on every tool call. Additionally, the fetch operation runs synchronously on the event loop without a timeout, causing the client to stall indefinitely if the target URL accepts the connection but does not respond. This vulnerability affects applications using the SDK as an MCP client (ClientSession, ClientSessionGroup, or 2.x Client) when calling tools on untrusted servers. The issue is fixed in versions 1.30.0 (1.x) and 2.2.0 (2.x) by restricting reference resolution to within the schema document and standard metaschemas, preventing network or file access during validation.

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 30 Oct 2026, 08:46 UTC

Technical details

References

Community reviews

Related threats