AI agents call get_docker_containers 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 a list of containers from a Docker/Podman host. It queries infrastructure state without modifying, executing code, deleting resources, or moving money. The blast radius of misuse is minimal—an agent could enumerate containers to plan further attacks, but cannot directly harm systems or data with this tool alone.
From the tool's definition Tool name 'get_docker_containers' and description 'Get containers on a specific host' indicate a retrieval/query operation with no side effects. The verb 'get' and absence of any modification, deletion, or execution language confirms read-only behavior.
Attacks that exploit this kind of access
Get containers on a specific host (works with both Docker and Podman). 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 get_docker_containers: 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.
get_docker_containers 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 get_docker_containers 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 get_docker_containers. 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.
get_docker_containers is provided by the Homelab MCP server (myraffy/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 →