start_container · MCP Developer Server MCP: Risk & Policy

WHAT IT DOES

What start_container does on MCP Developer Server

AI agents invoke start_container to trigger actions in MCP Developer Server. 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 start_container needs a policy

Starting a container is an Execute action because it triggers code/process execution in an isolated environment. While containerization provides safety boundaries, the tool initiates external operations whose behavior depends on the container's configuration and workload. This is not Read (no data retrieval), Write (not creating/modifying persistent data structures), Destructive (reversible), or Financial.

From the tool's definition Tool starts a stopped container, which executes operations within an isolated Docker environment. The description indicates it 'Start[s] a stopped container,' triggering external Docker runtime operations whose effects depend on the container's configured…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_container Rate-limited

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": {
    "start_container": {
      "limits": [
        {
          "counter": "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 MCP Developer Server, so you can run agents against it safely.

FAQ

Questions about start_container

What does the start_container tool do? +

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

How do I enforce a policy on start_container? +

Register the MCP Developer Server MCP server in PolicyLayer and add a rule for 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 MCP Developer Server. Nothing to install.

What risk level is start_container? +

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

Can I rate-limit start_container? +

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

Set action: deny in the PolicyLayer policy for 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 start_container? +

start_container is provided by the MCP Developer Server MCP server (ra86-dev/mcpdev-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.