docker_exec · MCP Container Tools MCP: Risk & Policy

WHAT IT DOES

What docker_exec does on MCP Container Tools

AI agents invoke docker_exec to trigger actions in MCP Container Tools. 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_exec needs a policy

This tool allows running arbitrary commands inside containers, which can modify system state, access sensitive data, exfiltrate information, or compromise the container and potentially the host system. The impact depends entirely on the command arguments provided by the user/agent, making it an Execute category risk with critical severity due to the broad potential for abuse and system compromise.

From the tool's definition Tool name 'docker_exec' and description 'Execute a command inside a running container' explicitly indicate arbitrary command execution within container environments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

docker_exec Rate-limited

docker_exec 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_exec": {
      "limits": [
        {
          "counter": "docker_exec_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 MCP Container Tools, so you can run agents against it safely.

FAQ

Questions about docker_exec

What does the docker_exec tool do? +

Execute a command inside a running container. It is categorised as a Execute tool in the MCP Container Tools 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_exec? +

Register the MCP Container Tools MCP server in PolicyLayer and add a rule for docker_exec: 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.

What risk level is docker_exec? +

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

Can I rate-limit docker_exec? +

Yes. Add a rate_limit block to the docker_exec 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_exec completely? +

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

docker_exec 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.