CVE-2026-31951CWE-200

LibreChat's MCP Server Header Injection Enables OAuth Token Theft

Medium · published March 27, 2026

CVSS v3.1
6.8
EPSS
0%
Percentile
27.7
In the wild
Unconfirmed
What it is

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.

The record
Technical detail
CVSS v3.1
6.8 · MEDIUM
Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
CVSS v4.0
Not supplied
EPSS
0.00353 · 27.7th percentile
Weakness
CWE-200 · Exposure of Sensitive Information to an Unauthorized Actor
Published
2026-03-27T19:29Z
EPSS history
Timeline
  • 27 MAR 19:29Z
    LibreChat's MCP Server Header Injection Enables OAuth Token Theft
    cvelistv5