MediumVulnerability
CVE-2026-54031: LibreChat MCP OAuth requests follow redirects to internal addresses
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-54031
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
Summary
LibreChat versions before 0.8.8 validate only the initial destination in createOAuthFetch (packages/api/src/mcp/oauth/handler.ts) for MCP OAuth discovery, registration, token, refresh, and revocation requests. The fetch then follows redirects without checking each redirect target. An attacker who can start MCP OAuth against a controlled endpoint can redirect server requests to internal or private addresses, bypassing the initial SSRF checks. The separate MCP transport path validates redirects and is not affected.
Mitigation
Fixed in 0.8.8.
Topics
Related items
- MediumCVE-2026-54026: LibreChat message injection via conversationId in request bodySimilar attack · NVD/CVE Database
- MediumCVE-2026-54046: LibreChat unauthenticated account enumeration via /api/user/verifySimilar attack · NVD/CVE Database
- HighCVE-2026-54044: LibreChat credential exposure through agent action domain repointingSimilar attack · NVD/CVE Database
- MediumCVE-2026-54043: LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7…Similar attack · NVD/CVE Database
- MediumCVE-2026-54042: LibreChat 2FA verification unlimited code guessing via temp token endpointSimilar attack · NVD/CVE Database