All vulnerabilities

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
Weakness
Information exposure through sent data (CWE-201)
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.

From LibreChat-AI/LibreChat's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
LibreChatServers and applications · cpe:a:librechat:librechat
  • Every version before 0.8.4
LibreChatServers and applications · github:librechat-ai/librechat
  • Version 0.8.3

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

From its GitHub repository.
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

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