AI agents invoke stop_server to trigger actions in Sacloud. 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.
This tool executes an infrastructure operation (stopping a server) whose effects depend on which server is targeted. While not destructive (the server can be restarted) and not immediately Financial, it is an Execute-category action because it triggers an external cloud operation with real consequences. The high severity reflects that an agent misusing this could disrupt production services.
From the tool's definition Tool name 'stop_server' indicates halting a running cloud server instance. Context: sibling tools include 'create_server', 'delete_bridge', 'delete_router', and other infrastructure management operations on Sakura Cloud (a Japanese cloud provider).
Documented attack patterns abuse exactly the kind of access stop_server gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sacloud, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_server:
{
"version": "1",
"default": "deny",
"tools": {
"stop_server": {
"limits": [
{
"counter": "stop_server_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_server 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.
stop_server. It is categorised as a Execute tool in the Sacloud MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sacloud MCP server in PolicyLayer and add a rule for stop_server: 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 Sacloud. Nothing to install.
stop_server 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 stop_server 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 stop_server. 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.
stop_server is provided by the Sacloud MCP server (sacloud/sacloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sacloud, 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.
37 Sacloud tools catalogued and risk-classified — across an index of 43,000+ MCP servers.