VulnerabilityPublished 23 Mar 2026

CVE-2026-33252: modelcontextprotocol go-sdk · Cross-Site Request Forgery (CSRF)

Affects modelcontextprotocol go-sdkSource CVE Database V5

Compare

Not known to be exploited · CVSS 7.1 High : upgrade to 1.4.1 soon.

Data as of 29 Oct 2026, 19:04 UTC

CVSS 3.1 base score

7.1High

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

EPSS: 0.1% chance of exploitation in 30 days – higher than 7% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 1.4.1

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: Required
Scope: Unchanged
Confidentiality: None
Integrity: High
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: 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: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to 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 23 Mar 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 go-sdk and github.com/modelcontextprotocol/go-sdk to 1.4.1.

Affected software

Product	Affected	Fixed in
modelcontextprotocolgo-sdk	Affected <1.4.1	Fixed in 1.4.1
Gogithub.com/modelcontextprotocol/go-sdk`pkg:golang/github.com/modelcontextprotocol/go-sdk`Other threats	Affected <1.4.1	Fixed in 1.4.1

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

AI-suggested

Upgrade the modelcontextprotocol go-sdk to version 1.4.1 or later immediately to apply the official patch addressing this vulnerability.
Implement strict validation of the Origin and Referer headers on the server side to ensure that only requests from trusted origins are processed.
Enforce the Content-Type header to be application/json for all MCP POST requests to prevent acceptance of cross-site form submissions with other content types.
Introduce or strengthen authorization mechanisms in MCP deployments, especially avoiding stateless or sessionless configurations without authentication.
Employ anti-CSRF tokens or similar mechanisms if the SDK or application allows customization to validate legitimate requests.
Monitor network traffic and logs for unusual POST requests to the MCP endpoints, particularly those originating from unexpected sources or with missing/incorrect headers.
Educate users about the risks of visiting untrusted websites that could trigger CSRF attacks.
Consider network-level controls such as firewall rules to restrict access to MCP services from untrusted networks or browsers. These measures collectively reduce the attack surface and prevent exploitation even if a user visits a malicious site.

Description

The Go MCP SDK used Go's standard encoding/json. Prior to version 1.4.1, the Go SDK's Streamable HTTP transport accepted browser-generated cross-site `POST` requests without validating the `Origin` header and without requiring `Content-Type: application/json`. In deployments without Authorization, especially stateless or sessionless configurations, this allows an arbitrary website to send MCP requests to a local server and potentially trigger tool execution. Version 1.4.1 contains a patch for the issue.

Impact

This vulnerability can have significant impacts on organizations deploying the affected go-sdk versions, especially those using the SDK in environments without robust authorization controls. Attackers can exploit the CSRF flaw to send unauthorized commands or trigger tool execution on local servers, potentially disrupting services or causing unintended operations. This compromises system integrity and availability, which can lead to operational downtime, loss of trust, and potential cascading failures if the tools executed have broader system privileges. Since the vulnerability requires user interaction (visiting a malicious website), phishing or social engineering campaigns could be used to facilitate exploitation. Organizations with stateless or sessionless MCP deployments are at higher risk because they lack the typical session-based protections against CSRF. Although no direct confidentiality breach is indicated, the ability to execute arbitrary commands can indirectly lead to data exposure or further compromise. The vulnerability affects any organization using the vulnerable SDK versions, particularly those in critical infrastructure, cloud services, or software development environments relying on the modelcontextprotocol go-sdk.

CWE-352Cross-Site Request Forgery (opens in a new tab)
Compound weaknessLikelihood of exploit: MediumCWE Top 25 (2025): #3OWASP Top 10 A01:2025: Broken Access Control (opens in a new tab)
The web application does not, or cannot, sufficiently verify whether a request was intentionally provided by the user who sent the request, which could have originated from an unauthorized actor.
Architecture and Design · Libraries or Frameworks
Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
Implementation
Ensure that the application is free of cross-site scripting issues (CWE-79), because most CSRF defenses can be bypassed using attacker-controlled script.
Architecture and Design
Generate a unique nonce for each form, place the nonce into the form, and verify the nonce upon receipt of the form. Be sure that the nonce is not predictable (CWE-330).
OWASP Cheat Sheets
REST Assessment (opens in a new tab)
REST Security (opens in a new tab)
Cross-Site Request Forgery Prevention (opens in a new tab)
Authorization Testing Automation (opens in a new tab)
Insecure Direct Object Reference Prevention (opens in a new tab)
OWASP ASVS 4.0.3
V13.2.3 (opens in a new tab)
V4.2.2 (opens in a new tab)
V13.3.2 (opens in a new tab)
Attack patterns
JSON Hijacking (aka JavaScript Hijacking) (opens in a new tab)
Cross-Domain Search Timing (opens in a new tab)
Cross Site Identification (opens in a new tab)
Cross Site 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 24 Mar 2026, 00:15 UTC

WeaknessesCWE-352

Technical details

References

Community reviews

Related threats