Severity by source
CVSS: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
Primary rating from GitHub Advisory · only source for this CVE.
CVSS VectorGitHub Advisory
CVSS: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
Lifecycle Timeline
4Blast Radius
ecosystem impact- 33 maven packages depend on io.modelcontextprotocol.sdk:mcp-core (12 direct, 21 indirect)
Ecosystem-wide dependent count for version 1.0.0.
DescriptionGitHub Advisory
Summary
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 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.
Details
Prior to 1.0.0 no Origin header validation was occurring, in violation of the MCP specification. Base Protocol > Transports: 2.0.1 Security Warning:
> 1: Servers MUST validate the Origin header on all incoming connections to prevent DNS rebinding attacks.
When the web server serving HTTP traffic to the MCP server does not perform standard CORS checks, a DNS rebinding attack is possible.
Some default server configurations and frameworks come with embedded Origin header validation. MCP servers built using those are not vulnerable to this issue. For example, the following are NOT vulnerable:
- Spring AI
Impact
Any developer connecting to a malicious website can inadvertently allow an attacker to make tool calls to local or private-network MCP servers.
Workarounds
Users can mitigate this risk by:
- Running the MCP server behind a reverse proxy (like Nginx or HAProxy) configured to strictly validate the
HostandOriginheaders. - Using a framework that inherently enforces strict CORS and Origin validation (such as Spring AI).
AnalysisAI
DNS rebinding in Model Context Protocol (MCP) Java SDK before v1.0.0 enables remote attackers to invoke arbitrary tool calls on local or network-private MCP servers via a victim's browser. The SDK failed to validate Origin headers per MCP specification requirements, violating mandatory server-side protections against cross-origin attacks. Exploitation requires social engineering (victim visits malicious site), but grants full tool invocation privileges as if the attacker were a locally authorized AI agent. Patch available in v1.0.0. No public exploit identified at time of analysis, but attack technique is well-understood (DNS rebinding). EPSS data not available; authentication requirements not confirmed from available data.
Technical ContextAI
The Model Context Protocol (MCP) is a framework for AI agents to interact with external tools and services via standardized server interfaces. The java-sdk (pkg:maven/io.modelcontextprotocol.sdk:mcp-core) provides server-side Java implementation for MCP tool hosting. Versions prior to 1.0.0 failed to implement mandatory Origin header validation specified in MCP 2025-06-18 Base Protocol Transport Security requirements. This omission creates a classic DNS rebinding vulnerability (CWE-346: Origin Validation Error), where an attacker controls a domain with rapidly-changing DNS records to bypass Same-Origin Policy protections. The attacker's page loads in victim's browser, DNS resolves to localhost/private IP, browser sends requests appearing to originate from trusted origin. Without server-side Origin validation, the MCP server accepts cross-origin requests from attacker-controlled pages targeting private network endpoints. Framework-specific mitigations exist: Spring AI provides built-in CORS/Origin enforcement, making Spring-based MCP servers immune even when using vulnerable SDK versions.
RemediationAI
Upgrade to Model Context Protocol Java SDK version 1.0.0 or later, which implements mandatory Origin header validation per MCP specification requirements. The patched release is available at github.com/modelcontextprotocol/java-sdk/releases/tag/v1.0.0 and via Maven Central. For environments unable to immediately upgrade, deploy MCP servers behind reverse proxy infrastructure configured to enforce strict Host and Origin header validation (Nginx, HAProxy, or equivalent). Alternatively, migrate to MCP server implementations using frameworks with built-in CORS protections such as Spring AI, which inherently validates Origin headers regardless of SDK version. Review network exposure of MCP servers and restrict access to trusted networks only. Developers should avoid accessing untrusted websites while running local MCP servers on development machines. Full advisory and remediation guidance available at github.com/modelcontextprotocol/java-sdk/security/advisories/GHSA-8jxr-pr72-r468.
Oracle Java SE 7 Update 6 and earlier contains multiple sandbox bypass vulnerabilities via the ClassFinder and forName m
Remote code execution in IBM Sterling B2B Integrator, Sterling Integrator, and Tivoli Common Reporting allows unauthenti
Java Runtime Environment sandbox bypass via incorrect image channel verification in 2D component allows remote unauthent
Oracle Java SE JDK/JRE 7 and 6 Update 27 and earlier allows remote code execution with complete system compromise throug
JBoss Seam 2 in Red Hat JBoss EAP 4.3.0 fails to sanitize JBoss Expression Language inputs, allowing remote attackers to
Unspecified vulnerability in the Java Runtime Environment (JRE) component in Oracle Java SE 7 update 4 and earlier, 6 up
Multiple vulnerabilities in Oracle Java 7 before Update 11 allow remote attackers to execute arbitrary code by (1) using
Unspecified vulnerability in the Java Runtime Environment (JRE) component in Oracle Java SE 7 Update 2 and earlier, 6 Up
The WLS Security component in Oracle WebLogic Server 10.3.6.0, 12.1.2.0, 12.1.3.0, and 12.2.1.0 allows remote attackers
Unspecified vulnerability in the Java Runtime Environment (JRE) component in Oracle Java SE 7 Update 7 and earlier allow
Remote unauthenticated attackers can execute arbitrary code on Adobe ColdFusion servers through Java deserialization fla
The ExceptionDelegator component in Apache Struts before 2.2.3.1 interprets parameter values as OGNL expressions during
Same weakness CWE-346 – Origin Validation Error
View allSame technique Information Disclosure
View allShare
External POC / Exploit Code
Leaving vuln.today
EUVD-2026-19954
GHSA-8jxr-pr72-r468