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
    • AI Data Pipelines
      Security Data Pipeline for AI SIEM and Data Optimization
    • 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-2026-33010

CVE-2026-33010: mcp-memory-service CSRF Vulnerability

CVE-2026-33010 is a CSRF flaw in mcp-memory-service that allows malicious websites to read, modify, and delete stored memories through misconfigured CORS settings. This article covers technical details, affected versions, and patches.

Published: March 27, 2026

CVE-2026-33010 Overview

CVE-2026-33010 is a critical CORS (Cross-Origin Resource Sharing) misconfiguration vulnerability in mcp-memory-service, an open-source memory backend for multi-agent systems. Prior to version 10.25.1, when the HTTP server is enabled (MCP_HTTP_ENABLED=true), the application configures FastAPI's CORSMiddleware with overly permissive settings including allow_origins=['*'], allow_credentials=True, allow_methods=["*"], and allow_headers=["*"]. This dangerous combination permits any website to read API responses cross-origin.

Critical Impact

When combined with anonymous access (MCP_ALLOW_ANONYMOUS_ACCESS=true), any malicious website can silently read, modify, and delete all stored memories without authentication, leading to complete compromise of stored data.

Affected Products

  • mcp-memory-service versions prior to 10.25.1
  • Deployments with MCP_HTTP_ENABLED=true configuration
  • Instances configured with MCP_ALLOW_ANONYMOUS_ACCESS=true

Discovery Timeline

  • 2026-03-20 - CVE-2026-33010 published to NVD
  • 2026-03-24 - Last updated in NVD database

Technical Details for CVE-2026-33010

Vulnerability Analysis

This vulnerability stems from an insecure default configuration in the FastAPI CORS middleware implementation. The combination of wildcard origin (*) with credentials support creates a scenario where browsers will include cookies and authentication headers in cross-origin requests while simultaneously allowing any domain to read the responses. This configuration violates the fundamental security principles of the Same-Origin Policy.

The vulnerability is classified under CWE-942 (Permissive Cross-domain Policy with Untrusted Domains). The attack requires user interaction—specifically, a victim must visit a malicious website while authenticated to the vulnerable mcp-memory-service instance. Once triggered, the attacker gains full read, write, and delete access to all stored memories in the multi-agent system.

Root Cause

The root cause is the misconfiguration of FastAPI's CORSMiddleware with overly permissive settings. Setting allow_origins=['*'] combined with allow_credentials=True is explicitly warned against in web security best practices, as it effectively disables cross-origin protections. When anonymous access is also enabled for convenience (the simplest way to get the HTTP dashboard working without OAuth), the attack surface expands to allow complete unauthenticated access from any origin.

Attack Vector

The attack vector is network-based and requires user interaction. An attacker can craft a malicious webpage containing JavaScript that makes cross-origin requests to a vulnerable mcp-memory-service instance. When a victim visits this page, the malicious JavaScript executes in their browser context and can:

  1. Enumerate all stored memories via API calls
  2. Exfiltrate sensitive data from the memory backend
  3. Modify existing memories to inject malicious content
  4. Delete critical memories, disrupting multi-agent system operations

The vulnerability manifests in the CORS middleware configuration within the FastAPI application. When a cross-origin request is made, the server responds with Access-Control-Allow-Origin: * header, permitting any origin to read the response. For technical implementation details, see the GitHub Security Advisory.

Detection Methods for CVE-2026-33010

Indicators of Compromise

  • Unusual cross-origin requests to mcp-memory-service API endpoints from external domains
  • Unexpected memory deletions or modifications in audit logs
  • API access patterns showing bulk data retrieval from unfamiliar IP addresses or referrer domains
  • JavaScript errors in browser console related to CORS on legitimate admin pages indicating potential tampering

Detection Strategies

  • Monitor HTTP request logs for requests with Origin headers from untrusted domains
  • Implement alerting on unusual API activity patterns such as bulk reads, deletions, or modifications
  • Deploy web application firewalls (WAF) to detect and block suspicious cross-origin request patterns
  • Review application configuration for insecure CORS settings during security audits

Monitoring Recommendations

  • Enable detailed logging for all API endpoints with origin and referrer tracking
  • Set up anomaly detection for memory access patterns in multi-agent system operations
  • Monitor for configuration changes to MCP_HTTP_ENABLED and MCP_ALLOW_ANONYMOUS_ACCESS settings
  • Implement real-time alerting on memory deletion events

How to Mitigate CVE-2026-33010

Immediate Actions Required

  • Upgrade mcp-memory-service to version 10.25.1 or later immediately
  • If immediate upgrade is not possible, disable HTTP server by setting MCP_HTTP_ENABLED=false
  • Disable anonymous access by setting MCP_ALLOW_ANONYMOUS_ACCESS=false and configure proper OAuth authentication
  • Review access logs for signs of exploitation and audit stored memories for unauthorized changes

Patch Information

The vulnerability has been patched in mcp-memory-service version 10.25.1. The patch addresses the insecure CORS configuration by implementing proper origin validation and removing the dangerous wildcard configuration. Organizations should upgrade to this version or later to remediate the vulnerability. For additional details, refer to the GitHub Security Advisory.

Workarounds

  • Disable HTTP server functionality entirely if not required by setting MCP_HTTP_ENABLED=false
  • Place the mcp-memory-service behind a reverse proxy that enforces strict CORS policies
  • Implement network-level access controls to restrict which domains can reach the service
  • Enable OAuth authentication and disable anonymous access (MCP_ALLOW_ANONYMOUS_ACCESS=false)
bash
# Configuration example - Secure mcp-memory-service settings
# Disable HTTP server if not required
export MCP_HTTP_ENABLED=false

# If HTTP is required, disable anonymous access
export MCP_ALLOW_ANONYMOUS_ACCESS=false

# Configure OAuth for proper authentication
# Refer to documentation for OAuth provider configuration

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

  • Vulnerability Details
  • TypeCSRF

  • Vendor/TechMcp Memory Service

  • SeverityHIGH

  • CVSS Score8.1

  • EPSS Probability0.03%

  • Known ExploitedNo
  • CVSS Vector
  • CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N
  • Impact Assessment
  • ConfidentialityLow
  • IntegrityHigh
  • AvailabilityNone
  • CWE References
  • CWE-942
  • Technical References
  • GitHub Security Advisory
  • Latest CVEs
  • CVE-2025-9185: Mozilla Firefox RCE Vulnerability

  • CVE-2025-9184: Mozilla Firefox RCE Vulnerability

  • CVE-2025-9180: Mozilla Firefox Auth Bypass Vulnerability

  • CVE-2025-8030: Mozilla Firefox RCE Vulnerability
Default Legacy - Prefooter | 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