Remove a saved watch.
AI agents call remove_watch to permanently remove resources in TalkDB — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a saved watch permanently deletes a scheduled query/alert configuration. This is irreversible without a backup or restore mechanism, placing it in the Destructive category. Severity is medium because the blast radius is limited to monitoring configurations rather than primary data, but losing watches could disable proactive alerts and monitoring.
From the tool's definition 'Remove a saved watch' — removing/deleting a saved monitoring configuration (watch) is an irreversible deletion of that resource.
Attacks that exploit this kind of access
Remove a saved watch. It is categorised as a Destructive tool in the TalkDB MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TalkDB MCP server in PolicyLayer and add a rule for remove_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 TalkDB. Nothing to install.
remove_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 remove_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 remove_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.
remove_watch is provided by the TalkDB MCP server (nitin-gupta1109/talkdb). 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 →