CVE-2026-31951 — LibreChat's MCP Server Header Injection Enables OAuth Token Theft

CVE-2026-31951

LibreChat's MCP Server Header Injection Enables OAuth Token Theft PUBLISHED

Description (CNA)

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 (CNA)

Vendor / product	Versions
danny-avila / LibreChat	affected >= v0.8.2-rc1, <= v0.8.3-rc1

CWE

CWE-200

References

https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954

ADP enrichment

CISA-ADP

No English description supplied.

No references supplied.