manage_containers · MCP Software Engineer MCP: Risk & Policy

WHAT IT DOES

What manage_containers does on MCP Software Engineer

AI agents invoke manage_containers to trigger actions in MCP Software Engineer. 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 manage_containers needs a policy

Managing Docker containers constitutes executing operations against live infrastructure. While the description is sparse, container management typically includes starting/stopping/restarting containers and potentially running commands inside them. This has significant blast radius as misuse could disrupt running services, expose sensitive data, or compromise system integrity.

From the tool's definition 'Manage Docker containers' — container management involves starting, stopping, restarting, and inspecting containers, which are external runtime operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

manage_containers Rate-limited

manage_containers 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": {
    "manage_containers": {
      "limits": [
        {
          "counter": "manage_containers_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 Software Engineer, so you can run agents against it safely.

FAQ

Questions about manage_containers

What does the manage_containers tool do? +

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

How do I enforce a policy on manage_containers? +

Register the MCP Software Engineer MCP server in PolicyLayer and add a rule for manage_containers: 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 Software Engineer. Nothing to install.

What risk level is manage_containers? +

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

Can I rate-limit manage_containers? +

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

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

manage_containers is provided by the MCP Software Engineer MCP server (rajawatrajat/mcp-software-engineer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.