All vulnerabilities

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

Affected software

SoftwareAffected versions
LibreChatServers and applications · cpe:a:librechat:librechat
  • From 0.8.2 before 0.8.3
  • Version 0.8.3-rc1
LibreChatServers and applications · github:librechat-ai/librechat
  • From 0.8.2-rc1 before 0.8.3-rc2

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-2026-31951
  • 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