AI agents invoke stop_instance to trigger actions in Scrapybara MCP. 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 a command against external infrastructure to halt a running service. While it is reversible (instances can be restarted), it irreversibly stops active operations on that instance, disrupts any processes running within it, and impacts resource availability.
From the tool's definition stop_instance stops a running Scrapybara instance, which halts an external operation/service. The Scrapybara MCP description states it 'enables AI clients to interact with virtual Ubuntu desktops...and control instances'.
Documented attack patterns abuse exactly the kind of access stop_instance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Scrapybara MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_instance:
{
"version": "1",
"default": "deny",
"tools": {
"stop_instance": {
"limits": [
{
"counter": "stop_instance_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_instance 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 a running Scrapybara instance. It is categorised as a Execute tool in the Scrapybara MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scrapybara MCP server in PolicyLayer and add a rule for stop_instance: 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 Scrapybara MCP. Nothing to install.
stop_instance 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_instance 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_instance. 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_instance is provided by the Scrapybara MCP server (scrapybara/scrapybara-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Scrapybara MCP, 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.
5 Scrapybara MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.