{"id":"CVE-2026-31951","aliases":["EUVD-2026-16769","GHSA-pmw7-gqwj-f954"],"status":"published","title":"LibreChat's MCP Server Header Injection Enables OAuth Token Theft","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.","severity":{"version":"3.1","score":6.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-12","score":0.00253,"percentile":0.17012,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-200"],"published":"2026-03-27T19:29:25Z","modified":"2026-10-28T02:30:52Z","products":[{"vendor":"danny-avila","product":"librechat"},{"vendor":"librechat","product":"librechat"}],"references":[{"url":"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954","tags":["x_refsource_CONFIRM","Exploit","Vendor Advisory","advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/31xxx/CVE-2026-31951.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-31951","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2026-31951","title":"LibreChat's MCP Server Header Injection Enables OAuth Token Theft","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.","status":"published","published":"2026-03-27T19:29:25.892Z","modified":"2026-03-31T13:46:25.297Z","cvss":[{"version":"3.1","score":6.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N","level":"medium","assessor":"cna"}],"cwes":["CWE-200"],"updated_at":"2026-11-02T14:19:51.277563Z"}],"euvd":[{"id":"EUVD-2026-16769","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.","status":"published","published":"2026-03-27T19:29:25Z","modified":"2026-03-31T13:46:25Z","cvss":[{"version":"3.1","score":6.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N","level":"medium"}],"updated_at":"2026-11-02T19:25:25.377294Z"}],"nvd":[{"id":"CVE-2026-31951","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.","status":"published","published":"2026-03-27T20:16:30.397Z","modified":"2026-10-26T21:10:00.17Z","cvss":[{"version":"3.1","score":6.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N","level":"medium","assessor":"secondary"},{"version":"3.1","score":5.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:N/A:N","level":"medium","assessor":"primary"}],"cwes":["CWE-200"],"updated_at":"2026-11-02T14:12:11.678711Z"}],"osv":[{"id":"CVE-2026-31951","title":"LibreChat's MCP Server Header Injection Enables OAuth Token Theft","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.","status":"published","published":"2026-03-27T19:29:25.892Z","modified":"2026-10-28T02:30:52.120874721Z","cvss":[{"version":"3.1","score":6.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N","level":"medium"}],"cwes":["CWE-200"],"updated_at":"2026-11-02T15:45:01.218144Z"}]}}