AI agents invoke liara_start_app to trigger actions in Liara 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.
Starting an application or scaling it up constitutes executing an external operation whose effects depend on which app is targeted and current infrastructure state. While not destructive (reversible via stop/scale down) or financial (no direct money movement), it triggers live infrastructure changes that qualify as Execute.
From the tool's definition Tool name 'liara_start_app' with description 'Start an app (scale up)' indicates execution of operational commands that trigger external infrastructure changes.
Documented attack patterns abuse exactly the kind of access liara_start_app gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Liara MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for liara_start_app:
{
"version": "1",
"default": "deny",
"tools": {
"liara_start_app": {
"limits": [
{
"counter": "liara_start_app_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}liara_start_app 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 an app (scale up). It is categorised as a Execute tool in the Liara MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Liara MCP Server MCP server in PolicyLayer and add a rule for liara_start_app: 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 Liara MCP Server. Nothing to install.
liara_start_app 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 liara_start_app 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 liara_start_app. 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.
liara_start_app is provided by the Liara MCP Server MCP server (razavioo/liara-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Liara 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.
108 Liara MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.