List Docker containers (local or remote)
AI agents call docker_ps to retrieve information from MCP Container Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs container enumeration/discovery, analogous to the 'ps' command in Docker. It only retrieves and displays information about running or existing containers; it does not create, modify, delete, execute code, or move money. This is a classic Read operation with minimal blast radius—the worst outcome is information disclosure about container state.
From the tool's definition Tool name 'docker_ps' and description 'List Docker containers (local or remote)' indicate a read-only query operation that retrieves container status information without modification or side effects.
Attacks that exploit this kind of access
List Docker containers (local or remote). It is categorised as a Read tool in the MCP Container Tools MCP Server, which means it retrieves data without modifying state.
Register the MCP Container Tools MCP server in PolicyLayer and add a rule for 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 MCP Container Tools. Nothing to install.
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 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 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.
docker_ps is provided by the MCP Container Tools MCP server (simseksem/mcp-container-tools). 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 →