docker_container_start · Docker MCP: Risk & Policy

WHAT IT DOES

What docker_container_start does on Docker MCP

AI agents invoke docker_container_start to trigger actions in Docker MCP. 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 docker_container_start needs a policy

This tool executes container startup, which runs pre-configured code in the container environment. While not destructive (reversible via stop), it can trigger side effects depending on container configuration (e.g., starting a container with malicious or unintended payloads, resource exhaustion, or network operations). The blast radius is significant in multi-container or production environments.

From the tool's definition Tool directly triggers external operations: 'Start a stopped container' - initiates state changes in Docker containers and can trigger arbitrary container code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

docker_container_start Rate-limited

docker_container_start 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": {
    "docker_container_start": {
      "limits": [
        {
          "counter": "docker_container_start_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, so you can run agents against it safely.

FAQ

Questions about docker_container_start

What does the docker_container_start tool do? +

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

How do I enforce a policy on docker_container_start? +

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

What risk level is docker_container_start? +

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

Can I rate-limit docker_container_start? +

Yes. Add a rate_limit block to the docker_container_start 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 docker_container_start completely? +

Set action: deny in the PolicyLayer policy for docker_container_start. 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 docker_container_start? +

docker_container_start is provided by the Docker MCP server (sondt2709/docker-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.