Servers and applications
CVE-2026-44653
Shared MCP Server View Leaks Decrypted Admin Secrets
- Severity
- Medium 6.5
- Published
- 2 Jun 2026
- Last changed
- 21 Jul 2026
- Added to UpHeron
- 1 Nov 2026
- Fixed in
- 0.8.4
- Exploit chance
- 0.3% in the next 30 daysHigher than 20% of CVEs. EPSS by FIRST, 19 Nov 2026
- Attack
- Over the network · Needs a user account · No user action needed
- Attacker can
- Read data
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N- Also known as
- GHSA-6vqg-rgpm-qvf9
- Sources
- NVD, Project advisories (GitHub)
Description
Users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through:
- GET /api/mcp/servers
- GET /api/mcp/servers/:serverName
The returned config includes plaintext values for:
- apiKey.key
- oauth.client_secret
This allows viewers of a shared MCP server to exfiltrate the underlying provider credentials.
The MCP registry decrypts sensitive server configuration before returning it:
- ServerConfigsDB.mapDBServerToParsedConfig() calls decryptConfig()
- decryptConfig() decrypts:
- apiKey.key when source === 'admin'
- oauth.client_secret
The route handlers then return the parsed config directly:
- getMCPServersList() returns getAllServerConfigs(userId)
- getMCPServerById() returns getServerConfig(serverName, userId)
Access control only requires VIEW on the MCP server for the single-server route. There is no redaction step for decrypted secrets before responding.
Affected software
| Software | Affected versions |
|---|---|
LibreChatServers and applications · cpe:a:librechat:librechat |
|
LibreChatServers and applications · github:librechat-ai/librechat |
|
About LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
- Docker Hub pulls
- 669,094Docker Hub, 15 Nov 2026
- GitHub stars
- 47,138GitHub, 15 Nov 2026
- Forks
- 9,706GitHub, 15 Nov 2026
- License
- MITGitHub
- First published on GitHub
- 12 Feb 2023GitHub
Source code Website Docker image
Vulnerabilities in LibreChat
- In our list
- 104
- Published in the last 12 months
- 84
- Critical, last 12 months
- 5
- High, last 12 months
- 25
- Known exploited
- 0
- CVE-2026-54041Plaintext password logged on login validation errorLow 3.1 17 Nov 2026
- CVE-2026-54032Remote MCP Server Description XSS via Unsanitized dangerouslySetInnerHTML; secondary Admin Banner sink lacks DOMPurifyMedium 6.1 17 Nov 2026
- CVE-2026-54026Cross-User Message Injection via Parameter Confusion in LibreChatMedium 6.5 17 Nov 2026
- CVE-2026-54031MCP OAuth requests can follow redirects to internal URLs after SSRF validationMedium 6.3 17 Nov 2026
- CVE-2026-54038Server-Side ReDoS via Unescaped Regex in Principal SearchMedium 6.5 17 Nov 2026
- CVE-2026-54045Password Reset Can Wipe Email-Verification Tokens When Verification Is EnforcedMedium 6.5 17 Nov 2026
References
- NVD https://nvd.nist.gov/vuln/detail/CVE-2026-44653
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-44653
- GitHub Advisory Database https://github.com/advisories/GHSA-6vqg-rgpm-qvf9
- github.com https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-6vqg-rgpm-qvf9