LibreChat server-side request forgery in MCP OAuth redirect handling
- Exploited
- No known exploitation
- Fix
- Fixed in 0.8.8
- Who is exposed
- Not reported
Summary
LibreChat, the AI chat application, has a flaw in how it handles MCP OAuth requests: after checking the first destination for internal addresses, it follows redirects without checking where they lead. An attacker who has low-privilege access and can start an MCP OAuth flow against a server they control can reach remotely, without user action, internal or private services that those checks should block.
Written by a model
Original 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.
What to do
Upgrade to a fixed version: 0.8.8.
Check your systems with an agent
Paste this into a coding or ops agent. It checks your systems read-only and reports a table per asset.
Check whether my systems are affected by CVE-2026-54031 (LibreChat: MCP OAuth requests can follow redirects to internal URLs after SSRF validation), using the cve.now data below.
Rules: work read-only. Do not run exploit code, proof-of-concept scripts or scanners that send attack payloads, and do not change any configuration, package, image or deployment. Report findings only.
What cve.now has for CVE-2026-54031 (entry last updated 2026-11-20):
Affected:
- LibreChat-AI LibreChat: fixed in 0.8.8
Fixed versions: 0.8.8.
Setup: unknown whether the bug needs a non-default feature or setting. Check the advisory.
CISA KEV: CVE-2026-54031 is not listed as of cve.now's last read.
This KEV status is for CVE-2026-54031 only. If you also check another CVE, look up its own KEV status; never assume it from this one.
How to check:
- Installed software: check what is actually running, not what a repo declares. Read the version from each host, container image and Kubernetes node (the binary's version output, the OS package database, image layers), and check whether the conditions above hold there. Distribution packages may carry a backported fix under an older version number; confirm against the distribution's own advisory.
Verify against the linked advisories before concluding, and cite the date you read each one:
- https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-f7xq-83jc-cgrj
- https://github.com/LibreChat-AI/LibreChat/pull/16514
- https://github.com/LibreChat-AI/LibreChat/commit/4d33d8c2c71ad497fdfaa2c4334b0a2293bcbd67
- https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.8
- https://www.librechat.ai/changelog/v0.8.8
Do not conclude an asset is unaffected unless you checked it and the evidence covers both its version and the conditions above. If you could not check something, mark it unknown and say what is missing.
Report a table with one row per asset and these columns: Asset | Version or build | Status (affected, fixed, not applicable, unknown) | Compensating controls | Exposure (internet-facing, internal, none) | Evidence | Next action.
Entry: https://cve.now/CVE-2026-54031
For follow-up questions, use the cve.now MCP server at https://mcp.cve.now/mcp (no authentication), for example execute with name cve.get and arguments {"id": "CVE-2026-54031"}.Affected versions
- LibreChat-AI LibreChatfixed in 0.8.8
cve.now Index
- Exploitation?/40Unknown. No CISA SSVC exploitation rating yet
- Exposure3/25Reachable over the network · Unknown: No advisory context yet
- Reach?/20Unknown. No tracked technology or package matched
- Severity6.3/10CVSS 6.3
- No patch0/5No signal
What would change the score
- Would score about 64 if added to CISA KEV
- Would score about 59 if CISA's SSVC rates exploitation active
- Would score about 28 if advisories confirm default setups are exposed
Timeline
- CVE published
- First seen by cve.now
Evidence 7
| Kind | Source |
|---|---|
| Vendor advisory 2Establishes: Affected and fixed versions. | |
| Advisory | GitHub · LibreChat-AI/LibreChat · Advisory GHSA-f7xq-83jc-cgrj |
| Link | librechat.ai · changelog/v0.8.8 |
| CVE record 2Establishes: The identifier and description. | |
| Record | CVE List · CVE-2026-54031 |
| Record | NVD · CVE-2026-54031 |
| Other links 3 | |
| Repository | GitHub · LibreChat-AI/LibreChat · Pull request #16514 |
| Repository | GitHub · LibreChat-AI/LibreChat · Commit 4d33d8c2 |
| Repository | GitHub · LibreChat-AI/LibreChat · Release v0.8.8 |
Questions about CVE-2026-54031
Is CVE-2026-54031 being exploited?
It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked.
Source: cve.now feed data
Which versions are affected by CVE-2026-54031?
LibreChat: before 0.8.8.
Source: cve.now feed data
How do I fix CVE-2026-54031?
Upgrade to a fixed version: 0.8.8.
Source: cve.now feed data
Related
- CVE-2026-54044LibreChat: Shared-Agent Editor Can Exfiltrate Owner Action API Keys via OpenAPI Spec Swap
- CVE-2026-54026LibreChat: Cross-User Message Injection via Parameter Confusion
- CVE-2026-54038LibreChat: Server-Side ReDoS via Unescaped Regex in Principal Search
- CVE-2026-54046LibreChat: Unauthenticated User Enumeration via Email Verification Endpoint
- CVE-2026-130235Improper Request URL Validation in the Okta .NET SDK Abstractions Library
- CVE-2026-77315Flyto2 Core: http.paginate follows server-supplied next-page URLs (Link header / cursor) without SSRF revalidation
No corrections so far. Something wrong on this page? Report an error.