Stop and remove a watcher
AI agents call cancel_watch to permanently remove resources in Loopsense — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling and removing a watcher permanently deletes its configuration and stops its monitoring activity. Unlike a pause, removal cannot be undone without recreating the watcher from scratch, making this a destructive operation. Blast radius is medium since it affects monitoring continuity rather than production data or systems directly.
From the tool's definition 'Stop and remove a watcher' — the removal is irreversible; the watcher configuration is deleted, not paused
Attacks that exploit this kind of access
Stop and remove a watcher. It is categorised as a Destructive tool in the Loopsense MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Loopsense MCP server in PolicyLayer and add a rule for cancel_watch: 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 Loopsense. Nothing to install.
cancel_watch 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 cancel_watch 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 cancel_watch. 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.
cancel_watch is provided by the Loopsense MCP server (jarvisassistantux/loopsense). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →