Every CVESearch/Get API key

CVE-2026-31951

LibreChat's MCP Server Header Injection Enables OAuth Token Theft

6.8 Medium

CVE-2026-31951 is a medium vulnerability (CVSS 6.8) in Danny-avila Librechat, published March 27, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.26%, the 17th percentile. No source names a fixed version.

What does this mean?
Severity
6.8 MediumCVSS 3.1, CVE List
Exploit chance
0.26%EPSS, 17th percentile
Exploitation
None knownNot on CISA’s or ENISA’s lists
Fixed in
No fix listedNo source names one

Description

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, 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. Version 0.8.3-rc2 fixes the issue.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
Low
User interaction
Required

What an attacker can affect

Confidentiality
High
Integrity
None
Availability
None

Exploit likelihood

0.26%Up 0.2 points since Mar 28, 2026
90%50%10%1%

Affected products

What each source reports

CVE List Score used6.8

LibreChat's MCP Server Header Injection Enables OAuth Token Theft

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, 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. Version 0.8.3-rc2 fixes the issue.

Record
CVE-2026-31951
CVSS 3.1
6.8 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
Weakness
CWE-200
Updated
2026-11-02
EUVDEUVD-2026-167696.8

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, 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. Version 0.8.3-rc2 fixes the issue.

Record
EUVD-2026-16769
CVSS 3.1
6.8 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
Updated
2026-11-02
NVD6.8

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, 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. Version 0.8.3-rc2 fixes the issue.

Record
CVE-2026-31951
CVSS 3.1
6.8 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
CVSS 3.1
5.7 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:N/A:N
Weakness
CWE-200
Updated
2026-11-02
OSV6.8

LibreChat's MCP Server Header Injection Enables OAuth Token Theft

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, 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. Version 0.8.3-rc2 fixes the issue.

Record
CVE-2026-31951
CVSS 3.1
6.8 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N
Weakness
CWE-200
Updated
2026-11-02

History

History
RecordedChangedSources
first indexedCVE List, EUVD, NVD, OSV

Dates are when Every CVE recorded each change. Upstream dates may differ.

References

MoveEnter Open