The SentinelOne Annual Threat Report - A Defenders Guide from the FrontlinesThe SentinelOne Annual Threat ReportGet the Report
Experiencing a Breach?Blog
Get StartedContact Us
SentinelOne
  • Platform
    Platform Overview
    • Singularity Platform
      Welcome to Integrated Enterprise Security
    • AI for Security
      Leading the Way in AI-Powered Security Solutions
    • Securing AI
      Accelerate AI Adoption with Secure AI Tools, Apps, and Agents.
    • How It Works
      The Singularity XDR Difference
    • Singularity Marketplace
      One-Click Integrations to Unlock the Power of XDR
    • Pricing & Packaging
      Comparisons and Guidance at a Glance
    Data & AI
    • Purple AI
      Accelerate SecOps with Generative AI
    • Singularity Hyperautomation
      Easily Automate Security Processes
    • AI-SIEM
      The AI SIEM for the Autonomous SOC
    • Singularity Data Lake
      AI-Powered, Unified Data Lake
    • Singularity Data Lake for Log Analytics
      Seamlessly Ingest Data from On-Prem, Cloud or Hybrid Environments
    Endpoint Security
    • Singularity Endpoint
      Autonomous Prevention, Detection, and Response
    • Singularity XDR
      Native & Open Protection, Detection, and Response
    • Singularity RemoteOps Forensics
      Orchestrate Forensics at Scale
    • Singularity Threat Intelligence
      Comprehensive Adversary Intelligence
    • Singularity Vulnerability Management
      Application & OS Vulnerability Management
    • Singularity Identity
      Identity Threat Detection and Response
    Cloud Security
    • Singularity Cloud Security
      Block Attacks with an AI-Powered CNAPP
    • Singularity Cloud Native Security
      Secure Cloud and Development Resources
    • Singularity Cloud Workload Security
      Real-Time Cloud Workload Protection Platform
    • Singularity Cloud Data Security
      AI-Powered Threat Detection for Cloud Storage
    • Singularity Cloud Security Posture Management
      Detect and Remediate Cloud Misconfigurations
    Securing AI
    • Prompt Security
      Secure AI Tools Across Your Enterprise
  • Why SentinelOne?
    Why SentinelOne?
    • Why SentinelOne?
      Cybersecurity Built for What’s Next
    • Our Customers
      Trusted by the World’s Leading Enterprises
    • Industry Recognition
      Tested and Proven by the Experts
    • About Us
      The Industry Leader in Autonomous Cybersecurity
    Compare SentinelOne
    • Arctic Wolf
    • Broadcom
    • CrowdStrike
    • Cybereason
    • Microsoft
    • Palo Alto Networks
    • Sophos
    • Splunk
    • Trellix
    • Trend Micro
    • Wiz
    Verticals
    • Energy
    • Federal Government
    • Finance
    • Healthcare
    • Higher Education
    • K-12 Education
    • Manufacturing
    • Retail
    • State and Local Government
  • Services
    Managed Services
    • Managed Services Overview
      Wayfinder Threat Detection & Response
    • Threat Hunting
      World-Class Expertise and Threat Intelligence
    • Managed Detection & Response
      24/7/365 Expert MDR Across Your Entire Environment
    • Incident Readiness & Response
      DFIR, Breach Readiness, & Compromise Assessments
    Support, Deployment, & Health
    • Technical Account Management
      Customer Success with Personalized Service
    • SentinelOne GO
      Guided Onboarding & Deployment Advisory
    • SentinelOne University
      Live and On-Demand Training
    • Services Overview
      Comprehensive Solutions for Seamless Security Operations
    • SentinelOne Community
      Community Login
  • Partners
    Our Network
    • MSSP Partners
      Succeed Faster with SentinelOne
    • Singularity Marketplace
      Extend the Power of S1 Technology
    • Cyber Risk Partners
      Enlist Pro Response and Advisory Teams
    • Technology Alliances
      Integrated, Enterprise-Scale Solutions
    • SentinelOne for AWS
      Hosted in AWS Regions Around the World
    • Channel Partners
      Deliver the Right Solutions, Together
    • SentinelOne for Google Cloud
      Unified, Autonomous Security Giving Defenders the Advantage at Global Scale
    • Partner Locator
      Your Go-to Source for Our Top Partners in Your Region
    Partner Portal→
  • Resources
    Resource Center
    • Case Studies
    • Data Sheets
    • eBooks
    • Reports
    • Videos
    • Webinars
    • Whitepapers
    • Events
    View All Resources→
    Blog
    • Feature Spotlight
    • For CISO/CIO
    • From the Front Lines
    • Identity
    • Cloud
    • macOS
    • SentinelOne Blog
    Blog→
    Tech Resources
    • SentinelLABS
    • Ransomware Anthology
    • Cybersecurity 101
  • About
    About SentinelOne
    • About SentinelOne
      The Industry Leader in Cybersecurity
    • Investor Relations
      Financial Information & Events
    • SentinelLABS
      Threat Research for the Modern Threat Hunter
    • Careers
      The Latest Job Opportunities
    • Press & News
      Company Announcements
    • Cybersecurity Blog
      The Latest Cybersecurity Threats, News, & More
    • FAQ
      Get Answers to Our Most Frequently Asked Questions
    • DataSet
      The Live Data Platform
    • S Foundation
      Securing a Safer Future for All
    • S Ventures
      Investing in the Next Generation of Security, Data and AI
  • Pricing
Get StartedContact Us
CVE Vulnerability Database
Vulnerability Database/CVE-2026-33252

CVE-2026-33252: Go MCP SDK CSRF Vulnerability

CVE-2026-33252 is a cross-site request forgery flaw in Go MCP SDK that allows arbitrary websites to send unauthorized MCP requests to local servers. This article covers technical details, affected versions, and patches.

Published: March 27, 2026

CVE-2026-33252 Overview

A Cross-Site Request Forgery (CSRF) vulnerability has been identified in the Go MCP SDK's Streamable HTTP transport prior to version 1.4.1. The vulnerability stems from the SDK accepting browser-generated cross-site POST requests without validating the Origin header and without requiring Content-Type: application/json. In deployments lacking Authorization, particularly stateless or sessionless configurations, this flaw allows arbitrary websites to send MCP requests to local servers and potentially trigger unauthorized tool execution.

Critical Impact

Malicious websites can exploit this vulnerability to execute MCP tool commands on local servers without user consent, potentially leading to unauthorized actions and data manipulation in vulnerable deployments.

Affected Products

  • Go MCP SDK versions prior to 1.4.1
  • Deployments using Streamable HTTP transport without Authorization
  • Stateless or sessionless MCP server configurations

Discovery Timeline

  • 2026-03-24 - CVE CVE-2026-33252 published to NVD
  • 2026-03-24 - Last updated in NVD database

Technical Details for CVE-2026-33252

Vulnerability Analysis

This vulnerability falls under CWE-352 (Cross-Site Request Forgery). The Go MCP SDK's Streamable HTTP transport implementation failed to implement proper safeguards against cross-origin requests. The core issue lies in two missing validation checks: the Origin header verification and the Content-Type: application/json requirement.

When a web browser makes cross-site POST requests, it typically includes an Origin header indicating the source domain. Servers should validate this header to ensure requests originate from trusted sources. Additionally, requiring specific content types like application/json acts as a defense mechanism because browsers cannot set custom Content-Type headers for cross-origin requests without triggering CORS preflight checks.

Without these validations, any malicious website could craft requests that appear legitimate to the MCP server, bypassing the browser's same-origin policy protections. This is particularly dangerous in local development environments where MCP servers may run without authentication.

Root Cause

The root cause is the absence of proper cross-origin request validation in the Streamable HTTP transport layer. The SDK used Go's standard encoding/json library but did not implement the necessary security headers validation that would prevent CSRF attacks. The server accepted POST requests regardless of their origin and without enforcing content-type restrictions that would normally trigger browser CORS preflight requests.

Attack Vector

An attacker can exploit this vulnerability by hosting a malicious webpage that automatically submits cross-site POST requests to a victim's local MCP server. The attack requires user interaction (visiting the malicious page) but no further user consent. The attack flow involves:

  1. Victim runs an MCP server locally without Authorization enabled
  2. Victim visits attacker-controlled webpage
  3. Malicious JavaScript on the page sends POST requests to the local MCP server
  4. Server processes requests without validating origin, executing MCP tools

The security patch addresses this by adding validation for both Origin and Content-Type headers:

go
//go:generate weave -o ../../docs/server.md ./server.src.md
//go:generate weave -o ../../docs/troubleshooting.md ./troubleshooting.src.md
//go:generate weave -o ../../docs/rough_edges.md ./rough_edges.src.md
//go:generate weave -o ../../docs/mcpgodebug.md ./mcpgodebug.src.md

// The doc package generates the documentation at /doc, via go:generate.
//

Source: GitHub Commit

Detection Methods for CVE-2026-33252

Indicators of Compromise

  • Unexpected MCP tool executions in server logs without corresponding legitimate user actions
  • HTTP POST requests to MCP endpoints with unusual or missing Origin headers
  • Server access logs showing requests from browser user agents with cross-origin referrers
  • Anomalous patterns of tool execution that coincide with user web browsing activity

Detection Strategies

  • Monitor MCP server logs for requests lacking proper Origin header validation
  • Implement network traffic analysis to detect cross-origin POST requests to local MCP endpoints
  • Review application logs for unexpected tool execution patterns
  • Deploy web application firewalls to detect and block suspicious cross-site request patterns

Monitoring Recommendations

  • Enable verbose logging on MCP servers to capture all incoming request headers
  • Set up alerts for MCP tool executions that occur without accompanying authentication events
  • Monitor for requests with Content-Type values other than application/json
  • Implement anomaly detection for unusual request patterns targeting MCP endpoints

How to Mitigate CVE-2026-33252

Immediate Actions Required

  • Upgrade Go MCP SDK to version 1.4.1 or later immediately
  • Enable Authorization on all MCP server deployments, especially those accessible via HTTP
  • Review and audit existing MCP server configurations for missing authentication
  • Implement network segmentation to limit access to local MCP servers

Patch Information

The vulnerability is patched in Go MCP SDK version 1.4.1. The patch implements proper validation of Origin and Content-Type headers in the Streamable HTTP transport layer. For detailed information, refer to the GitHub Security Advisory GHSA-89xv-2j6f-qhc8 and the security patch commit.

Workarounds

  • Enable Authorization on MCP servers even in development environments
  • Configure reverse proxies to validate Origin headers before forwarding requests
  • Restrict MCP server binding to localhost with additional network controls
  • Implement CORS policies at the infrastructure level if SDK upgrade is not immediately possible
bash
# Configuration example
# Update go.mod to use patched version
go get github.com/modelcontextprotocol/go-sdk@v1.4.1

# Verify the updated version
go list -m github.com/modelcontextprotocol/go-sdk

Disclaimer: This content was generated using AI. While we strive for accuracy, please verify critical information with official sources.

  • Vulnerability Details
  • TypeCSRF

  • Vendor/TechGo

  • SeverityHIGH

  • CVSS Score7.1

  • EPSS Probability0.01%

  • Known ExploitedNo
  • CVSS Vector
  • CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:L
  • Impact Assessment
  • ConfidentialityLow
  • IntegrityHigh
  • AvailabilityLow
  • CWE References
  • CWE-352
  • Technical References
  • GitHub Commit Update

  • GitHub Security Advisory GHSA-89xv-2j6f-qhc8
  • Related CVEs
  • CVE-2026-27896: Go MCP SDK Auth Bypass Vulnerability

  • CVE-2025-61731: Go cmd/go Path Traversal Vulnerability

  • CVE-2025-4674: Go Command RCE Vulnerability in VCS

  • CVE-2023-24531: Go Environment Command RCE Vulnerability
Experience the World’s Most Advanced Cybersecurity Platform

Experience the World’s Most Advanced Cybersecurity Platform

See how our intelligent, autonomous cybersecurity platform can protect your organization now and into the future.

Try SentinelOne
  • Get Started
  • Get a Demo
  • Product Tour
  • Why SentinelOne
  • Pricing & Packaging
  • FAQ
  • Contact
  • Contact Us
  • Customer Support
  • SentinelOne Status
  • Language
  • Platform
  • Singularity Platform
  • Singularity Endpoint
  • Singularity Cloud
  • Singularity AI-SIEM
  • Singularity Identity
  • Singularity Marketplace
  • Purple AI
  • Services
  • Wayfinder TDR
  • SentinelOne GO
  • Technical Account Management
  • Support Services
  • Verticals
  • Energy
  • Federal Government
  • Finance
  • Healthcare
  • Higher Education
  • K-12 Education
  • Manufacturing
  • Retail
  • State and Local Government
  • Cybersecurity for SMB
  • Resources
  • Blog
  • Labs
  • Case Studies
  • Videos
  • Product Tours
  • Events
  • Cybersecurity 101
  • eBooks
  • Webinars
  • Whitepapers
  • Press
  • News
  • Ransomware Anthology
  • Company
  • About Us
  • Our Customers
  • Careers
  • Partners
  • Legal & Compliance
  • Security & Compliance
  • Investor Relations
  • S Foundation
  • S Ventures

©2026 SentinelOne, All Rights Reserved.

Privacy Notice Terms of Use

English