Description
Token Optimizer MCP measures token savings per AI coding agent, optimizes context, and shares a live local knowledge graph across 16 CLI clients. Prior to version 5.1.0, token-optimizer-mcp is vulnerable to OS command injection in the smart_user tool. Any MCP client that can call the smart_user tool can execute arbitrary shell commands through the username argument of the get-user-info operation. The commands execute with the privileges of the user running the token-optimizer-mcp server. This issue has been patched in version 5.1.0.
Published: 2026-09-28
Score: 8.4 High
EPSS: < 1% Very Low
KEV: No
Impact: Remote Code Execution
Action: Patch Immediately
AI Analysis

Impact

Token Optimizer MCP allows an attacker to execute arbitrary shell commands by supplying a crafted username to the get-user-info operation of the smart_user tool. The injected commands run with the privileges of the user that runs the token-optimizer-mcp server, enabling complete compromise of that host. This flaw is enumerated as CWE-78 (OS Command Injection) and can lead to full system takeover if the server user is privileged.

Affected Systems

The vulnerability affects the token-optimizer-mcp product from ooples, specifically any deployment with a server version older than 5.1.0. All 16 CLI clients that communicate with the server are potentially able to trigger the command injection by calling the smart_user tool. Versions 5.1.0 and later have the issue fixed.

Risk and Exploitability

The CVSS score of 8.4 signals a high severity and indicates that both confidentiality, integrity, and availability are at risk. The EPSS score is not available, and the vulnerability is not listed in the CISA KEV catalog, implying no known widespread exploitation at the time of this analysis. The likely attack vector is via any MCP client that can invoke the smart_user tool; this requires network access to the server and knowledge of the get‑user‑info command. Since the injection occurs in a user-supplied argument, exploitation is straightforward if the attacker can reach the relevant endpoint.

Generated by OpenCVE AI on September 28, 2026 at 19:24 UTC.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Apply the vendor patch by upgrading token-optimizer-mcp to version 5.1.0 or newer
  • If patching is delayed, restrict network access to the smart_user endpoint or limit client permissions so that only trusted users can invoke get-user-info
  • Consider running the token-optimizer-mcp server under a least-privilege account or in an isolated container to contain potential damage if the command injection is exploited

Generated by OpenCVE AI on September 28, 2026 at 19:24 UTC.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-49mq-fc6q-3h46 Token Optimizer MCP: OS command injection in smart_user via username in get-user-info
History

Thu, 01 Oct 2026 15:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}


Mon, 28 Sep 2026 20:15:00 +0000

Type Values Removed Values Added
First Time appeared Ooples
Ooples token-optimizer-mcp
Vendors & Products Ooples
Ooples token-optimizer-mcp

Mon, 28 Sep 2026 18:00:00 +0000

Type Values Removed Values Added
Description Token Optimizer MCP measures token savings per AI coding agent, optimizes context, and shares a live local knowledge graph across 16 CLI clients. Prior to version 5.1.0, token-optimizer-mcp is vulnerable to OS command injection in the smart_user tool. Any MCP client that can call the smart_user tool can execute arbitrary shell commands through the username argument of the get-user-info operation. The commands execute with the privileges of the user running the token-optimizer-mcp server. This issue has been patched in version 5.1.0.
Title Token Optimizer MCP: OS command injection in smart_user via username in get-user-info
Weaknesses CWE-78
References
Metrics cvssV3_1

{'score': 8.4, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'}


Subscriptions

Ooples Token-optimizer-mcp
cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-10-01T14:47:57.868Z

Reserved: 2026-06-16T15:13:28.165Z

Link: CVE-2026-55157

cve-icon Vulnrichment

Updated: 2026-10-01T14:47:40.828Z

cve-icon NVD

Status : Deferred

Published: 2026-09-28T18:17:23.373

Modified: 2026-10-01T15:17:30.207

Link: CVE-2026-55157

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-09-28T19:41:57Z

Weaknesses
  • CWE-78

    Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')