Vulnerability · Published Mar 27, 2026 · Assigned by GitHub_M

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

Medium 6.8

In plain English

A medium-severity information exposure in LibreChat from danny-avila. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 17% of all known vulnerabilities).

Severity (CVSS 3.1)6.8Medium

Exploit odds (30 days)0.3%top 83.1% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

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

Weakness: CWE-200 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N

References

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