stop_container · Docker MCP Server MCP: Risk & Policy

WHAT IT DOES

What stop_container does on Docker MCP Server

AI agents invoke stop_container to trigger actions in Docker MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why stop_container needs a policy

While 'stop' might sound like a simple command, it is an Execute-class action: it causes the Docker daemon to perform an operation that changes the state of a running container. It is not Destructive because the container and its data remain; the container can be restarted. It is not Write (which creates/modifies data reversibly within a system) but rather triggers an external service operation.

From the tool's definition Tool description states 'Stop a running Docker container' — this triggers an external operation (Docker daemon) whose effects depend on which container is targeted. Stopping a container is a state-changing action on a live service.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_container Rate-limited

stop_container stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "stop_container": {
      "limits": [
        {
          "counter": "stop_container_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Docker MCP Server, so you can run agents against it safely.

FAQ

Questions about stop_container

What does the stop_container tool do? +

Stop a running Docker container. It is categorised as a Execute tool in the Docker MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_container? +

Register the Docker MCP Server MCP server in PolicyLayer and add a rule for stop_container: 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 Docker MCP Server. Nothing to install.

What risk level is stop_container? +

stop_container is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit stop_container? +

Yes. Add a rate_limit block to the stop_container 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.

How do I block stop_container completely? +

Set action: deny in the PolicyLayer policy for stop_container. 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.

What MCP server provides stop_container? +

stop_container is provided by the Docker MCP Server MCP server (swartdraak/docker-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.