mittwald_container_run · Mittwald MCP Server MCP

WHAT IT DOES

What mittwald_container_run does on Mittwald MCP Server

AI agents invoke mittwald_container_run to trigger actions in Mittwald MCP 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 mittwald_container_run needs a policy

Creating and starting a container is a direct code execution primitive. An AI agent given this tool can run arbitrary workloads, install software, access host resources, exfiltrate data, or pivot to other systems — depending entirely on what container image and entrypoint arguments are provided.

From the tool's definition Tool description states 'Create and start a new container' — this launches arbitrary containerized code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mittwald_container_run Rate-limited

mittwald_container_run 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": {
    "mittwald_container_run": {
      "limits": [
        {
          "counter": "mittwald_container_run_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 Mittwald MCP Server, so you can run agents against it safely.

FAQ

Questions about mittwald_container_run

What does the mittwald_container_run tool do? +

Create and start a new container. It is categorised as a Execute tool in the Mittwald MCP 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 mittwald_container_run? +

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

What risk level is mittwald_container_run? +

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

Can I rate-limit mittwald_container_run? +

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

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

mittwald_container_run is provided by the Mittwald MCP Server MCP server (mittwald/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.