Cyber Resilience

CVE-2026-35568

Lfprojects Mcp Java Sdk ≤ 1.0.0

Published
07 April 2026
Modified
24 July 2026
Patch / advisory
CVSS Score v4 7.6
Click a component to see what it means
Raw vectorCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS Score 0.0014 4th percentile
Risk Priority 55 floored blend · peak EPSS

Summary

CVE-2026-35568 is a high-severity Origin Validation Error (CWE-346) vulnerability in Lfprojects Mcp Java Sdk. Its CVSS base score is 7.6 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Drive-by Compromise (T1189); ranked at the 4th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.

The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and SC-7 (Boundary Protection) — see the control section below for these in your framework.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

MCP Java SDK is the official Java SDK for Model Context Protocol servers and clients. Prior to 1.0.0, the java-sdk contains a DNS rebinding vulnerability. This vulnerability allows an attacker to access a locally or network-private java-sdk MCP server via…

more

a victims browser that is either local, or network adjacent. This allows an attacker to make any tool call to the server as if they were a locally running MCP connected AI agent. This vulnerability is fixed in 1.0.0.

CWE(s)

AI Security AnalysisAI

AI Category
AI Agent Protocols and Integrations
Risk Domain
Protocol-Specific Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: ai, mcp, model context protocol

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1189 Drive-by Compromise Initial Access
Adversaries may gain access to a system through a user visiting a website over the normal course of browsing.
T1557.001 Name Resolution Poisoning and SMB Relay Credential Access
By responding to LLMNR/NBT-NS/mDNS network traffic, adversaries may spoof an authoritative source for name resolution to force communication with an adversary controlled system.
Why these techniques?

DNS rebinding vuln (CWE-346) enables browser-based access to private MCP server via malicious site visit (drive-by) and name resolution poisoning to bypass SOP.

Confidence: MEDIUM · MITRE ATT&CK Enterprise v19.0

CVEs Like This One

CVE-2026-34237Same product: Lfprojects Mcp Java Sdk
CVE-2025-14279Same vendor: Lfprojects
CVE-2026-59950Same vendor: Lfprojects
CVE-2026-2611Same vendor: Lfprojects
CVE-2025-66414Same vendor: Lfprojects
CVE-2025-66416Same vendor: Lfprojects
CVE-2026-33252Same vendor: Lfprojects
CVE-2026-27896Same vendor: Lfprojects
CVE-2025-10193Shared CWE-346
CVE-2026-44429Same vendor: Lfprojects

Affected Assets

lfprojects
mcp java sdk
≤ 1.0.0

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)
  • AC-3 Access Enforcement
  • SC-7 Boundary Protection
  • AC-4 Information Flow Enforcement
Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)
  • 3 hardening rules · 1 OS baseline
Validate
Prove the fix (OWASP ASVS)

Mitigating Controls (NIST 800-53 r5) AI

prevent

Enforces access decisions so that only locally-connected MCP agents (not browser-originated requests) can invoke tools on the SDK server.

prevent

Boundary-protection mechanisms can block or isolate the MCP server endpoint from browser-initiated cross-origin traffic that arrives via DNS rebinding.

prevent

Information-flow rules can be configured to reject requests whose origin does not match an authorized local MCP client, mitigating the origin-validation flaw.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.AA-03 mostly match
prevents

Authentication directly verifies the source of users/services/hardware, mitigating origin validation failures.

PR.AA-04 mostly match
prevents

Verifying identity assertions enforces origin validation for conveyed claims.

ID.AM-03 partial match
prevents

Documenting authorized flows supports origin validation by defining expected sources.

PR.IR-01 partial match
prevents

Protecting networks from unauthorized access requires origin checks on communication sources.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

mitigates

Network security controls enforce origin validation at network boundaries.

mitigates

Security of network services includes validating the authenticity of service endpoints.

mitigates

Network segregation reduces exposure but does not directly validate origins.

prevents

Application security requirements explicitly call for origin validation of inputs and communications.

prevents

Secure architecture principles encourage origin checks but do not mandate them.

prevents

Secure coding practices include implementing proper origin validation to prevent spoofing.

References