Delete a watch and all its snapshots.
AI agents call delete_watch to permanently remove resources in Mcp Watched — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible deletion of data. Once a watch and its snapshots are deleted, they cannot be recovered through normal operations. This is a destructive action with potential for significant data loss if invoked incorrectly by an AI agent, warranting the Destructive category and high severity rating.
From the tool's definition Tool name is 'delete_watch' and description states 'Delete a watch and all its snapshots' - uses explicit 'Delete' verb and indicates irreversible removal of data (watch configuration and all associated snapshots).
Attacks that exploit this kind of access
Delete a watch and all its snapshots. It is categorised as a Destructive tool in the Mcp Watched MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Watched MCP server in PolicyLayer and add a rule for delete_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 Mcp Watched. Nothing to install.
delete_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 delete_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 delete_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.
delete_watch is provided by the Mcp Watched MCP server (ng-pr0ject/mcp-watched). 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 →