Every CVE Search/ Get API key

CVE-2026-31944

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

7.6 High

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.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
Low
User interaction
Required

What an attacker can affect

Confidentiality
High
Integrity
Low
Availability
None

Exploit likelihood

0.26%Up 0.2 points since Mar 14, 2026
90%50%10%1%

What each source reports

CVE List Score used 7.6

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

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.

Record
CVE-2026-31944
CVSS 3.1
7.6 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N
Weakness
CWE-306
Updated
2026-11-02
EUVDEUVD-2026-12092 7.6

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.

Record
EUVD-2026-12092
CVSS 3.1
7.6 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N
Updated
2026-11-02
NVD 7.6

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.

Record
CVE-2026-31944
CVSS 3.1
7.6 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N
Weakness
CWE-306
Updated
2026-11-02
OSV 7.6

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

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.

Record
CVE-2026-31944
CVSS 3.1
7.6 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N
Weakness
CWE-306
Updated
2026-11-02

Affected products

History

History
RecordedChangedSources
first indexedCVE List, EUVD, NVD, OSV

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

CVE-2026-31944 is a high vulnerability (CVSS 7.6) in Danny-avila Librechat, published March 13, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.26%, the 17th percentile. No source names a fixed version.

References

MoveEnter Open