Stop and remove an active directory watch.
AI agents call unwatch to permanently remove resources in Filesystem Watcher MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
'Unwatch' terminates and removes an active watch configuration. This action is not easily reversible — the watch state (including any buffered or pending events) is lost. While it doesn't delete filesystem data, it irreversibly removes an active monitoring session. Misuse by an AI agent could silently blind the system to filesystem changes, potentially causing missed events in critical workflows.
From the tool's definition Stop and remove an active directory watch
Attacks that exploit this kind of access
Stop and remove an active directory watch. It is categorised as a Destructive tool in the Filesystem Watcher MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Filesystem Watcher MCP server in PolicyLayer and add a rule for unwatch: 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 Filesystem Watcher MCP. Nothing to install.
unwatch 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 unwatch 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 unwatch. 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.
unwatch is provided by the Filesystem Watcher MCP server (trycatchkamal/filesystemwatcher-mcp). 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 →