delete_client
AI agents call delete_client to permanently remove resources in Clockify Time Tracking — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The 'delete' prefix unambiguously signals irreversible removal of data. In the context of a time-tracking system, deleting a client would permanently remove that client entity and likely associated records. This is a destructive action with potential business impact (loss of client relationship history, project associations, billing records).
From the tool's definition Tool name is 'delete_client' which indicates irreversible deletion of client data. The description is empty, but the name clearly indicates a destructive operation that cannot be undone.
Attacks that exploit this kind of access
delete_client. It is categorised as a Destructive tool in the Clockify Time Tracking MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Clockify Time Tracking MCP server in PolicyLayer and add a rule for delete_client: 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 Clockify Time Tracking. Nothing to install.
delete_client 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_client 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_client. 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_client is provided by the Clockify Time Tracking MCP server (pypi:clockify-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 →