CVE-2026-44653: LibreChat Shared MCP Server View Leaks Decrypted Admin Secrets

Published Jun 2, 2026
·
Updated

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through GET /api/mcp/servers and GET /api/mcp/servers/:serverName. The returned config includes plaintext values for apiKey.key and oauth.clientsecret. This allows viewers of a shared MCP server to exfiltrate the underlying provider credentials. Version 0.8..4 contains a patch. Other remediations include: never returning decrypted admin-managed secrets to non-owners; redacting apiKey.key and oauth.clientsecret from all API responses consider returning only boolean presence indicators for secrets, similar to the auth-values route pattern; and, if owners need to edit configs without re-entering secrets, preserving secrets server-side and returning placeholders instead of plaintext.

Affected Software

2 affected components
librechat LibreChat MCP Server<=0.8.3
librechat librechat<0.8.4

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade to a fixed release to a version that resolves this vulnerability.

    Fixed in 0.8..4
  2. Configuration

    For non-owner users with only VIEW access, ensure GET /api/mcp/servers and GET /api/mcp/servers/:serverName never return decrypted admin-managed secrets. Specifically, redact apiKey.key and oauth.client_secret from API responses; optionally return only boolean presence indicators (or placeholders) rather than plaintext. If owners need to edit configs without re-entering secrets, preserve secrets server-side and return placeholders instead of plaintext.

    MCP server API endpoints GET /api/mcp/servers and GET /api/mcp/servers/:serverName secret handling = Do not return decrypted admin-managed secret plaintext (e.g., redact apiKey.key and oauth.client_secret); return only boolean presence indicators or placeholders instead of plaintext

Event History

Jun 2, 2026
CVE Published
via MITRE·10:40 PM
Data Sourced
via MITRE·10:40 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·11:16 PM
DescriptionSeverityWeaknessAffected Software
Free Weekly Intel

Don't miss critical vulnerabilities

Join thousands of security professionals who receive our weekly digest of trending CVEs, zero-days, and exploited vulnerabilities.

No spam. Unsubscribe anytime.

Frequently Asked Questions

1

What is the severity of CVE-2026-44653?

The severity of CVE-2026-44653 is medium with a CVSS score of 6.5.

2

How do I fix CVE-2026-44653?

To fix CVE-2026-44653, update LibreChat to version 0.8.4 or later.

3

What can be compromised due to CVE-2026-44653?

CVE-2026-44653 allows users with `VIEW` access to retrieve decrypted admin-managed secrets.

4

Which versions of LibreChat are affected by CVE-2026-44653?

Versions of LibreChat up to and including 0.8.3 are affected by CVE-2026-44653.

5

What type of access is exploited in CVE-2026-44653?

CVE-2026-44653 exploits users with only `VIEW` access to an MCP server.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203