CVE-2026-35568 — mcp-core
CVE-2026-35568 is a CWE-346 vulnerability in io.modelcontextprotocol.sdk:mcp-core. A fix is available for io.modelcontextprotocol.sdk:mcp-core — see the affected versions and patch details below.
MCP Java-SDK has a DNS Rebinding Vulnerability
Exploitation Status
No confirmed exploitation observed yet
- A successful exploit gives an attacker total control of the affected component, not partial access.
- CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.
Exploitation and automatability from CISA’s SSVC triage for CVE-2026-35568.
EPSS Exploitation Probability
EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.
Real-World Exposure
io.modelcontextprotocol.sdk:mcp-coreReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects Maven packages — download data is not available via public APIs for these ecosystems.
Description
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).
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| ☕Maven | io.modelcontextprotocol.sdk:mcp-core | all versions | 1.0.0io.modelcontextprotocol.sdk:mcp-core:1.0.0 |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for io.modelcontextprotocol.sdk:mcp-core, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update io.modelcontextprotocol.sdk:mcp-core to 1.0.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-35568 is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 Security's impact-aware SCA analyses which vulnerable code paths your application actually calls, so a match like CVE-2026-35568 can be triaged on real exposure rather than presence alone.
Tailored to CVE-2026-35568. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Frequently Asked Questions
Is CVE-2026-35568 in your dependencies?
O3 Security finds CVE-2026-35568 across Maven dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.