AI agents call watch_unregister to permanently remove resources in ScreenHand — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a watch rule by ID is an irreversible deletion of a configured automation/monitoring rule. Once removed, the rule configuration is gone and would need to be manually recreated. This fits the Destructive category as it permanently deletes a resource.
From the tool's definition Remove a watch rule by ID
Documented attack patterns abuse exactly the kind of access watch_unregister gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for watch_unregister:
{
"version": "1",
"default": "deny",
"hide": [
"watch_unregister"
]
}watch_unregister disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Remove a watch rule by ID. It is categorised as a Destructive tool in the ScreenHand MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ScreenHand MCP server in PolicyLayer and add a rule for watch_unregister: 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 ScreenHand. Nothing to install.
watch_unregister is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the watch_unregister 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 watch_unregister. 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.
watch_unregister is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, 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.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.