AI agents invoke deploy_stack to trigger actions in Komodo 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.
Deploying a stack executes infrastructure changes across servers and services. While not immediately destructive or financial, it triggers external operations whose effects are substantial and depend on which stack is targeted. The blast radius is high if an agent deploys an incorrect or malicious stack configuration.
From the tool's definition Tool name is 'deploy_stack' and description states 'Despliega un stack específico' (deploys a specific stack). Deploying infrastructure is an external operation that triggers real-world effects on live systems.
Documented attack patterns abuse exactly the kind of access deploy_stack gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Komodo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for deploy_stack:
{
"version": "1",
"default": "deny",
"tools": {
"deploy_stack": {
"limits": [
{
"counter": "deploy_stack_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}deploy_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.
Despliega un stack específico. It is categorised as a Execute tool in the Komodo MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Komodo MCP Server MCP server in PolicyLayer and add a rule for deploy_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 MCP Server. Nothing to install.
deploy_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 deploy_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 deploy_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.
deploy_stack is provided by the Komodo MCP Server MCP server (nonetss/komodo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Komodo MCP Server, 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.
54 Komodo MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.