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.

Severity (CVSS)

Base score8
SeverityHigh
VersionCVSS 3.1
VectorCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:N
Provided byCNA

Weaknesses

  • CWE-346 — CWE-346: Origin Validation Error

Affected products

VendorProductVersions
danny-avilaLibreChat< 0.8.5

References

Authoritative sources

This page is a snapshot. For the latest enrichment and updates, view the record on CVE.org or the NVD.

Generated from the official CVE List on 26 Jun 2026 07:05 UTC.