High Risk →

stop_stack

stop_stack

How to control stop_stack ↓

What stop_stack does on Komodo

AI agents invoke stop_stack to trigger actions in Komodo. 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.

High Risk

Why stop_stack needs a policy

The tool executes an operational command to stop infrastructure (a stack) in a DevOps platform, which is an external operation whose effects depend on which stack is targeted. This is not a Read (no retrieval), not Write (does not reversibly create/modify data), not Destructive (stopping is typically reversible; the stack can be restarted), not Financial.

From the tool's definition Tool name 'stop_stack' indicates it performs an action to stop a stack resource in the Komodo DevOps platform.

Documented attack patterns abuse exactly the kind of access stop_stack gives an agent:

How to control stop_stack

PolicyLayer is an MCP gateway — it sits between your AI agents and Komodo, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_stack:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "stop_stack": {
      "limits": [
        {
          "counter": "stop_stack_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

stop_stack 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.

  1. Create a free account and register Komodo — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about stop_stack

What does the stop_stack tool do? +

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

How do I enforce a policy on stop_stack? +

Register the Komodo MCP server in PolicyLayer and add a rule for stop_stack: 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 Komodo. Nothing to install.

What risk level is stop_stack? +

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

Can I rate-limit stop_stack? +

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

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

stop_stack is provided by the Komodo MCP server (myrikld/komodo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Komodo tool call.

Start from Komodo, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

53 Komodo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.