# CVE-2026-32625: LibreChat environment variable exfiltration in MCP server integration

Source: https://junglewise.ai/threats/cve-2026-32625-librechat-environment-variable-exfiltration-in-mcp-server  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-06-02. Updated: 2026-06-02  
License: CC BY 4.0 with a link back

CVE-2026-32625 · Severity: critical · CVSS 9.6 · Published 2026-06-02

LibreChat, an open-source AI interface for multiple providers, contains a critical flaw in how it handles server configurations. An authenticated user can trick the system into sending its internal security secrets—including database credentials and encryption keys—to an external server controlled by the attacker. This allows an attacker to gain full control over the application's data, forge user sessions, and access private API keys for AI services.

Technologies: [LibreChat](https://junglewise.ai/threats/technologies/librechat). Vendors: [LibreChat](https://junglewise.ai/threats/vendors/librechat).

## Quick answers

**Is CVE-2026-32625 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-32625 being exploited in the wild.

**How severe is CVE-2026-32625?** Critical severity, with a CVSS score of 9.6, published 2 June 2026.

**Which products and versions are affected?** LibreChat <= 0.8.3.

**Is there a fix for CVE-2026-32625?** A patch was published on 2026-06-02: Patched in v0.8.4-rc1 Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-32625 attacked?** It is attacked over the network, in a network appliance.

**Am I affected by CVE-2026-32625?** Check whether you run LibreChat at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

A vulnerability in LibreChat versions up to 0.8.3 exists within the Model Context Protocol (MCP) server integration. The application uses a Zod schema transformation that calls `extractEnvVariable` on user-supplied MCP server URLs, which resolves `${VAR}` placeholders against the server's `process.env`. An authenticated attacker can submit a malicious URL via the `POST /api/mcp/servers` endpoint containing environment variable references (e.g., `${JWT_SECRET}`). During schema validation and subsequent connection testing via `MCPServerInspector.inspect()`, the server resolves these variables and transmits them as part of an HTTP request to an attacker-controlled domain. This results in the exposure of critical secrets such as `CREDS_KEY`, `JWT_SECRET`, and `MONGO_URI`. The issue is patched in version 0.8.4-rc1.

## Affected products

- danny-avila LibreChat <= 0.8.3

## Timeline

- 2026-06-02: disclosed
- 2026-06-02: advisory
- 2026-06-02: patched: Patched in v0.8.4-rc1

## References

- [https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx](https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx)

## Related threats

- [LibreChat 2FA bypass via unauthenticated backup code regeneration](https://junglewise.ai/threats/cve-2026-54040-librechat-2fa-bypass-via-unauthenticated-backup-code-regeneration)
- [LibreChat resource exhaustion via missing rate limiting in duplicate endpoint](https://junglewise.ai/threats/cve-2026-54037-librechat-resource-exhaustion-via-missing-rate-limiting-in)
- [LibreChat SSRF via custom endpoint baseURL](https://junglewise.ai/threats/cve-2026-54033-librechat-ssrf-via-custom-endpoint-baseurl)
- [LibreChat token theft via missing OAuth resource validation in MCP](https://junglewise.ai/threats/cve-2026-54030-librechat-token-theft-via-missing-oauth-resource-validation-in)
- [danny-avila LibreChat IDOR in message deletion endpoint](https://junglewise.ai/threats/cve-2026-54029-danny-avila-librechat-idor-in-message-deletion-endpoint)