docker_run_container · Cargoshipper MCP: Risk & Policy

WHAT IT DOES

What docker_run_container does on Cargoshipper

AI agents invoke docker_run_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_run_container needs a policy

This tool runs Docker containers, which can execute arbitrary code with access to host resources, networks, volumes, and environment variables. An AI agent with access to this tool could deploy malicious containers, exfiltrate data, pivot to other systems, or disrupt infrastructure. The blast radius is severe because container execution is inherently open-ended—the actual effects depend entirely on what runs inside.

From the tool's definition Tool name 'docker_run_container' indicates execution of containerized code/applications. Server description states it 'provides Claude with direct access to Docker...for infrastructure management and automation.' The absence of a description is notable but…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

docker_run_container Rate-limited

docker_run_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_run_container": {
      "limits": [
        {
          "counter": "docker_run_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_run_container

What does the docker_run_container tool do? +

docker_run_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_run_container? +

Register the Cargoshipper MCP server in PolicyLayer and add a rule for docker_run_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_run_container? +

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

Can I rate-limit docker_run_container? +

Yes. Add a rate_limit block to the docker_run_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_run_container completely? +

Set action: deny in the PolicyLayer policy for docker_run_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_run_container? +

docker_run_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.