Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD 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.
Priority
LOW
Exploitation
NONE
PoC
YES
Patch
NONE
Momentum
NONE
If you run products in this scope, you should treat this CVE as relevant to your environment.
1 version affected across 1 product
CVE-2026-31951 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 arbitrar… https://www.cve.org/CVERecord?id=CVE-2026-31951
Post summary
The post references CVE‑2026‑31951 and notes a potential flaw in LibreChat MCP servers, but provides no concrete vulnerability details, exploit code, or mitigation guidance.
2 of 2 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | librechat | librechat | - | - | - |
| App | librechat | librechat | 0.8.3 | - | - |