LibreChat: MCP OAuth requests can follow redirects to internal URLs after SSRF validation
Summary
| CVE | CVE-2026-54031 |
|---|---|
| State | PUBLISHED |
| Assigner | GitHub_M |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2026-11-20 20:17:41 UTC |
| Updated | 2026-11-20 20:17:41 UTC |
| Description | 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. |
Risk And Classification
Primary CVSS: v3.1 6.3 MEDIUM from [email protected]
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N
Problem Types: CWE-918 | CWE-918 CWE-918: Server-Side Request Forgery
| Version | Source | Type | Score | Severity | Vector |
|---|---|---|---|---|---|
| 3.1 | [email protected] | Secondary | 6.3 | MEDIUM | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N |
| 3.1 | CNA | DECLARED | 6.3 | MEDIUM | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N |
CVSS v3.1 Breakdown
Attack Vector
NetworkAttack Complexity
HighPrivileges Required
LowUser Interaction
NoneScope
ChangedConfidentiality
HighIntegrity
NoneAvailability
NoneCVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|---|---|---|---|
| CNA | LibreChat-AI | LibreChat | affected < 0.8.8 | Not specified |
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| github.com/LibreChat-AI/LibreChat/pull/16514 | [email protected] | github.com | |
| github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-f7xq-83jc-cgrj | [email protected] | github.com | |
| github.com/LibreChat-AI/LibreChat/commit/4d33d8c2c71ad497fdfaa2c4334b0a2... | [email protected] | github.com | |
| github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.8 | [email protected] | github.com | |
| www.librechat.ai/changelog/v0.8.8 | [email protected] | www.librechat.ai | |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.