launch_stack · Sceptre MCP: Risk & Policy

WHAT IT DOES

What launch_stack does on Sceptre

AI agents invoke launch_stack to trigger actions in Sceptre. 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 launch_stack needs a policy

This tool executes CloudFormation stack operations (creation or updates) via Sceptre, which deploys infrastructure to AWS. While not immediately destructive like delete_stack, it materially alters cloud infrastructure state and incurs resource costs. It triggers external operations with side effects that depend on the caller's intent (the stack definition), making it Execute rather than Write.

From the tool's definition Tool name 'launch_stack' with description 'Launch a CloudFormation stack via Sceptre (create or update as needed)' indicates execution of infrastructure operations that can create or modify cloud resources.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_stack Rate-limited

launch_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "launch_stack": {
      "limits": [
        {
          "counter": "launch_stack_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 Sceptre, so you can run agents against it safely.

FAQ

Questions about launch_stack

What does the launch_stack tool do? +

Launch a CloudFormation stack via Sceptre (create or update as needed). It is categorised as a Execute tool in the Sceptre MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on launch_stack? +

Register the Sceptre MCP server in PolicyLayer and add a rule for launch_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 Sceptre. Nothing to install.

What risk level is launch_stack? +

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

Can I rate-limit launch_stack? +

Yes. Add a rate_limit block to the launch_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 launch_stack completely? +

Set action: deny in the PolicyLayer policy for launch_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 launch_stack? +

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