Servers and applications
CVE-2026-31951
MCP Server Header Injection Enables OAuth Token Theft
- Severity
- Medium 5.7
- Published
- 27 Mar 2026
- Last changed
- 26 Oct 2026
- Added to UpHeron
- 1 Nov 2026
- Fixed in
- 0.8.3-rc2, 0.8.3
- Exploit chance
- 0.3% in the next 30 daysHigher than 17% of CVEs. EPSS by FIRST, 19 Nov 2026
- Weakness
- Information exposure (CWE-200)
- Attack
- Over the network · Needs a user account · Needs someone to click or open something
- Attacker can
- Read data
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:N/A:N- Also known as
- GHSA-pmw7-gqwj-f954
- Sources
- NVD, Project advisories (GitHub)
Description
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.
The omitServerManagedFields() function filters dangerous fields from user-provided MCP server configurations, but critically omits headers from the blocklist. Combined with processMCPEnv() which substitutes credential placeholders in headers during tool calls, this allows credential theft.
- Initial connection/inspection: Headers are NOT substituted (no user context available)
- Subsequent tool calls: Headers ARE substituted with victim's credentials via setRequestHeaders()
- LibreChat instance with MCP servers enabled
- For OAuth token theft: OpenID SSO must be configured and victim must authenticate via SSO
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-2026-31951
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-31951
- GitHub Advisory Database https://github.com/advisories/GHSA-pmw7-gqwj-f954
- github.com https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954