Vulnerability  ·  2026-09-19

MKP (MCP server for Kubernetes) — unauthenticated pod log exfiltration via get_resource tool

VulnerabilityHigh impactGlobalCVE-2026-50125
MKP, a Model Context Protocol server that lets AI agents interact with Kubernetes clusters, exposed a log-retrieval tool over its default HTTP transport without any authentication check, letting any network client read pod logs.
Pod logs frequently contain secrets, tokens, and sensitive application data; an unauthenticated MCP tool that can be used to exfiltrate them from a Kubernetes cluster is a serious data-exposure risk wherever this AI-agent-to-Kubernetes bridge is deployed.
MKP's default HTTP endpoint registers the unauthenticated get_resource MCP tool, which accepts attacker-controlled limitBytes and tailLines parameters for the pods logs subresource, allowing a remote unauthenticated client to pull arbitrary pod logs from the cluster.
MKP (StacklokLabs) < 0.4.1
Upgrade to MKP 0.4.1 or later and ensure MCP tool endpoints require authentication before network exposure.
GitHub commit (fix)NVD CVE-2026-50125
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →