CVE-2026-31951 PUBLISHED

LibreChat's MCP Server Header Injection Enables OAuth Token Theft

Assigner: GitHub_M
Reserved: 10.03.2026 Published: 27.03.2026 Updated: 27.03.2026

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.

Metrics

CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
CVSS Score: 6.8

Product Status

Vendor danny-avila
Product LibreChat
Versions
  • Version >= v0.8.2-rc1, <= v0.8.3-rc1 is affected

References

Problem Types

  • CWE-200: Exposure of Sensitive Information to an Unauthorized Actor CWE