CVE-2026-54030 — HIGH (8.0)

Vulnerability Description

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Resource metadata (RFC 9728) matches the configured MCP server URL, allowing a malicious MCP server to steal access tokens intended for a legitimate server. This vulnerability is fixed in 0.8.5.

CVSS Score

8.0

HIGH

CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:N

Attack Vector

NETWORK

Attack Complexity

HIGH

Privileges Required

NONE

User Interaction

REQUIRED

Scope

CHANGED

Confidentiality

HIGH

Integrity

HIGH

Availability

NONE

Related Weaknesses (CWE)

CWE-346

References

FAQ

What is CVE-2026-54030?

CVE-2026-54030 is a vulnerability with a CVSS score of 8.0 (HIGH). LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Reso...

How severe is CVE-2026-54030?

CVE-2026-54030 has been rated HIGH with a CVSS base score of 8.0/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2026-54030?

Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.