What’s Vulnerable › Vulnerabilities
CVE-2026-31951: LibreChat's MCP Server Header Injection Enables OAuth Token Theft
- Severity: medium (CVSS 5.7 v3.1)
- Exploited in the wild: not listed in CISA KEV
- EPSS: 0.3% probability of exploitation in the next 30 days
- Public exploit or detection template: yes
- Published: 2026-03-27 · updated 2026-10-26
- Weakness: CWE-200
Description
LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue.
Affected products
- danny-avila LibreChat: from 0.8.2 before 0.8.3; 0.8.3-rc1 — fixed in 0.8.3
How to fix
Upgrade to a fixed version: danny-avila LibreChat 0.8.3. Check the vendor advisory for mitigations.
References
Get alerted when CVE-2026-31951 or the next vulnerability affects your stack