NewApp Monitoring is liveSign up free
AgentbeamBeta
AI agent vulnerability · Other MCP servers and tools

CVE-2026-45609: Spring AI MCP Security: Unvalidated URL Fetching (SSRF)

highCVSS 3.1 7.2GHSA-qjp4-4jvr-xqg3

Summary The mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol (MCP) security specifications. Specifically, it processes untrusted URLs for OAuth-related discovery and metadata without verifying if the targets are malicious or internal to the network.

Published May 18, 2026 · Updated Jun 9, 2026

Affected packages

org.springaicommunity:mcp-client-security

Ecosystem
Maven
Affected
< 0.1.9
Fixed in
0.1.9
Check
mvn dependency:tree -Dincludes=org.springaicommunity:mcp-client-security

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Summary

The mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol (MCP) security specifications. Specifically, it processes untrusted URLs for OAuth-related discovery and metadata without verifying if the targets are malicious or internal to the network.

This only affects installations with Dynamic Client Registration (DCR) enabled:

spring.ai.mcp.client.authorization.dynamic-client-registration.enabled=true

DCR does not validate URLs exposed by MCP Servers (protected resource metadata URL, authorization server URL) and Authorization Servers (all OAuth2 endpoints).

Workaround

When users need to perform DCR, they may provide their own McpOAuth2ClientManager. Both McpMetadataDiscoveryService and DynamicClientRegistrationService are also affected, if used, users should provide their own subclasses.

Alternatively, users can provide the default implementations of these classes with a RestClient that implements URL filtering through ClientHttpRequestInterceptor.

Credited to srikanthramu.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More Other MCP servers and tools vulnerabilities

All Other MCP servers and tools entries