docker_start_container · Cargoshipper MCP: Risk & Policy

WHAT IT DOES

What docker_start_container does on Cargoshipper

AI agents invoke docker_start_container to trigger actions in Cargoshipper. 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_start_container needs a policy

This tool triggers execution of code/services within Docker containers. While not immediately destructive, it has significant blast radius: an AI agent could inadvertently start containers running malicious code, consuming resources, or accessing sensitive data. This is Execute rather than Write because it activates/runs code rather than merely modifying configuration.

From the tool's definition The tool 'docker_start_container' is described as 'Start a stopped Docker container.' Starting a container executes and triggers the external operation of spinning up a containerized service, whose effects depend on what the container is configured to run.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

docker_start_container Rate-limited

docker_start_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": {
    "docker_start_container": {
      "limits": [
        {
          "counter": "docker_start_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 Cargoshipper, so you can run agents against it safely.

FAQ

Questions about docker_start_container

What does the docker_start_container tool do? +

Start a stopped Docker container. It is categorised as a Execute tool in the Cargoshipper 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_start_container? +

Register the Cargoshipper MCP server in PolicyLayer and add a rule for docker_start_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 Cargoshipper. Nothing to install.

What risk level is docker_start_container? +

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

Can I rate-limit docker_start_container? +

Yes. Add a rate_limit block to the docker_start_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 docker_start_container completely? +

Set action: deny in the PolicyLayer policy for docker_start_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 docker_start_container? +

docker_start_container is provided by the Cargoshipper MCP server (scarr7981/cargoshipper-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.