Home

Description

mcp-security provides Security and Authorization support for Model Context Protocol in Spring AI. Prior to 0.1.9, 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 This vulnerability is fixed in 0.1.9.

PUBLISHED Reserved 2026-05-12 | Published 2026-05-29 | Updated 2026-06-02 | Assigner GitHub_M




HIGH: 7.2CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N

Problem types

CWE-918: Server-Side Request Forgery (SSRF)

Product status

< 0.1.9
affected

References

github.com/...curity/security/advisories/GHSA-qjp4-4jvr-xqg3

cve.org (CVE-2026-45609)

nvd.nist.gov (CVE-2026-45609)

Download JSON