AI agents invoke start_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.
Starting a stack on a DevOps platform (Komodo) executes infrastructure operations whose effects depend on the stack configuration and state. This is not a simple read (no data retrieval), not a reversible write (starting is an operational trigger with side effects), and not explicitly destructive or financial.
From the tool's definition Tool name 'start_stack' in a DevOps platform context indicates it initiates containers or infrastructure; server description mentions 'stacks' as a managed resource alongside 'servers, containers, builds'.
Documented attack patterns abuse exactly the kind of access start_stack gives an agent:
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 start_stack:
{
"version": "1",
"default": "deny",
"tools": {
"start_stack": {
"limits": [
{
"counter": "start_stack_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_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.
Free to start. No card required.
start_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.
Register the Komodo MCP server in PolicyLayer and add a rule for start_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.
start_stack is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_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.
Set action: deny in the PolicyLayer policy for start_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.
start_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.
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.