CVE-2026-58197

8.8 HIGHpublic exploit available

Published 2026-09-18 · Updated 2026-09-24

AI risk analysis

Summary: The flaw allows local access to host services and other ToolHive-managed MCP proxies due to lack of network isolation, posing a high risk of data exposure and service disruption.
Exploitability: Exploitation is relatively easy as it requires local access to the MCP server container, which can be achieved through various means such as misconfigured systems or insider threats.
Blast radius: If exploited, this can lead to significant data exposure, unauthorized access to internal services, and potential disruption of managed services.
Detection: No reliable host or network indicator is derivable from the published description.
Prioritized remediation: Upgrade to ToolHive CLI 0.30.1 and ToolHive Studio 0.38.0 immediately.

rceauth-bypassnetworkcontainer

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

ToolHive is a utility designed to simplify the deployment and management of Model Context Protocol servers. Prior to ToolHive CLI 0.30.1 and ToolHive Studio 0.38.0, locally run MCP server containers use the default network permission profile without network isolation, permitting access to host.docker.internal while ToolHive API and MCP proxy endpoints are reachable without authentication. A malicious or compromised MCP server can use the Docker gateway to contact host-local services, other ToolHive-managed MCP proxies, or the ToolHive control plane without escaping the container. This access can expose data and logs, invoke sibling MCP tools, alter process or workload state, and disrupt services. ToolHive Studio additionally sends network_isolation as false and overrides the backend's secure isolation default. This issue is fixed in ToolHive CLI 0.30.1 and ToolHive Studio 0.38.0.

CVSS vector

CVSS:3.1/AV:A/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Weaknesses

CWE-284, CWE-306

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.