CVE-2026-31951

MEDIUM

LibreChat's MCP Server Header Injection Enables OAuth Token Theft

Title source: cna
STIX 2.1

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.

Scores

CVSS v3 6.8
EPSS 0.0004
EPSS Percentile 11.2%
Attack Vector NETWORK
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N

CISA SSVC

Vulnrichment
Exploitation poc
Automatable no
Technical Impact partial

Details

CWE
CWE-200
Status published
Products (3)
danny-avila/LibreChat >= v0.8.2-rc1, <= v0.8.3-rc1
librechat/librechat 0.8.3 rc1
librechat/librechat 0.8.2 - 0.8.3
Published Mar 27, 2026
Tracked Since Mar 29, 2026