CVE-2026-54031

published 20 Nov 2026 · updated 20 Nov 2026

LibreChat: MCP OAuth requests can follow redirects to internal URLs after SSRF validation

6.3MediumCVSS 6.3EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. No fixed version is recorded.

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.8, packages/api/src/mcp/oauth/handler.ts createOAuthFetch validates only the initial destination for MCP OAuth discovery, registration, token, refresh, and revocation requests, then uses redirect-following fetch behavior without validating each redirect target. An attacker who can initiate MCP OAuth against a controlled endpoint can redirect server requests to internal or private addresses, reaching services that the initial SSRF checks should block. The separate MCP transport path already validates redirects and is not affected. This issue is fixed in version 0.8.8.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
LibreChat-AI<0.8.8

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-54031 severity on Zeptric[![CVE-2026-54031](https://zeptric.io/badge/cve/CVE-2026-54031.svg)](https://zeptric.io/cve/CVE-2026-54031)