AI agents call devbox_docker_ps to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays the current state of Docker containers (analogous to the 'docker ps' command), which is a read-only operation with no side effects. It does not create, modify, delete, or execute any containers or code. The blast radius of misuse is minimal—an attacker would only gain visibility into running containers, not control over them.
From the tool's definition Tool name 'devbox_docker_ps' and description 'Show all running Docker containers on the devbox' indicate a query/list operation that retrieves status information without modification or execution.
Attacks that exploit this kind of access
Show all running Docker containers on the devbox. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for devbox_docker_ps: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Homelab. Nothing to install.
devbox_docker_ps is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the devbox_docker_ps rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for devbox_docker_ps. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
devbox_docker_ps is provided by the Homelab MCP server (nainounen/homelab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →