Findings

CVE-2026-31951

LibreChat is a ChatGPT clone with additional features.

Published Mar 27, 2026 · updated Jun 17, 2026 · librechat librechat

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 (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue.

Code

The project this record applies to. Exploit listings stay in References.

No public source repository is identified for this product.

Timeline

Detection, updates, and resolution for this record.

  1. Mar 27, 2026 · NIST NVD

    Detected

    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 (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated.

  2. Jun 17, 2026 · NIST NVD

    Updated

    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 (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated.

Affected

  • cpe librechat/librechatversion unspecified
  • cpe librechat/librechat0.8.3

Sources

  • CVE.orgVulnerability recordCVE-2026-31951

    Official CVE identifier

    cve.org
  • NIST NVDVulnerability recordCVE-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 arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server wit

    nvd.nist.gov

References

CVE-2026-31951 · ZeroDay Findings