CVE-2026-31944 LibreChat MCP OAuth callback does not validate browser session — allows token theft via redirect link

High 7.6 Published 13 Mar 2026 Updated 16 Mar 2026

Attackers can steal OAuth tokens by tricking victims into completing an MCP flow, leading to account takeover of linked services.

Exploited in the wild: Not known
Login needed: Any signed-in user
Attackable: Over the internet
Victim action needed: A user has to click or open something
Fix: None listed

What is CVE-2026-31944?

CVE-2026-31944 is a high-severity authentication bypass vulnerability in Librechat Librechat, published on 13 Mar 2026. Any signed-in user can exploit it over the network, and only if a user opens a file or follows a link.

Official 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.

Weakness: CWE-306

Which versions are affected by CVE-2026-31944?

It affects 1 product.

Products include Librechat Librechat.

How do I fix CVE-2026-31944?

No fix has been published for CVE-2026-31944 yet. Limit exposure of the affected software until one is available.

Upgrade, and rotate credentials and sessions that may have been exposed. More about Authentication bypass.

Is CVE-2026-31944 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-31944 exists.

All Librechat Librechat vulnerabilities

Sources

Also known as GHSA-vf7j-7mrx-hp7g.