CVE-2026-31944

LibreChat MCP OAuth callback does not validate browser session — allows token theft via redirect link

Published Mar 13, 2026 CVSS 3.1 · 7.6 High EPSS < 1% KEV · Not listed
Description
LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redirect URL is logged in or that the logged-in user matches the initiator. An attacker can send the authorization URL to a victim; when the victim completes the flow, the victim’s OAuth tokens are stored on the attacker’s LibreChat account, enabling account takeover of the victim’s MCP-linked services (e.g. Atlassian, Outlook). This vulnerability is fixed in 0.8.3-rc1.

Remediation

No solution or workaround provided in the CVE record

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
First Time appeared Librechat
Librechat librechat
CPEs cpe:2.3:a:librechat:librechat:0.8.2:-:*:*:*:*:*:*
cpe:2.3:a:librechat:librechat:0.8.2:rc1:*:*:*:*:*:*
cpe:2.3:a:librechat:librechat:0.8.2:rc2:*:*:*:*:*:*
cpe:2.3:a:librechat:librechat:0.8.2:rc3:*:*:*:*:*:*
Vendors & Products Librechat
Librechat librechat
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Danny-avila
Danny-avila libre Chat
Vendors & Products Danny-avila
Danny-avila libre Chat
Type Values Removed Values Added
Description LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redirect URL is logged in or that the logged-in user matches the initiator. An attacker can send the authorization URL to a victim; when the victim completes the flow, the victim’s OAuth tokens are stored on the attacker’s LibreChat account, enabling account takeover of the victim’s MCP-linked services (e.g. Atlassian, Outlook). This vulnerability is fixed in 0.8.3-rc1.
Title LibreChat MCP OAuth callback does not validate browser session — allows token theft via redirect link
Weaknesses CWE-306
References
Metrics cvssV3_1

{'score': 7.6, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Mar 16, 2026, 1:41 PM
Reserved
Mar 10, 2026, 3:10 PM
Status
Analyzed
Published
Mar 13, 2026, 7:54 PM
Modified
Jun 17, 2026, 10:34 AM