Delete an implementation item from a ticket
AI agents call delete_implementation_item to permanently remove resources in Tickr — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
number | string | Yes | Ticket display number, e.g. 'TKR-42' (legacy) or 'TKR-BUG-0042' (typed) |
item_id | string | Yes | Implementation item ID to delete |
Parameters from the server's own tool schema.
This tool irreversibly removes data (an implementation item) from a ticket in the project management system. It cannot be undone without restoring from backups or manual recreation. While not as critical as deleting entire tickets or projects, it still constitutes a destructive action on managed work items.
From the tool's definition Tool name is 'delete_implementation_item' with description 'Delete an implementation item from a ticket'. The verb 'delete' and the action of removing an implementation item are irreversible operations on project data.
Attacks that exploit this kind of access
Delete an implementation item from a ticket. It is categorised as a Destructive tool in the Tickr MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
delete_implementation_item accepts 2 parameters: number, item_id. Required: number, item_id. The full parameter table on this page comes from the server's own tool schema.
Register the Tickr MCP server in PolicyLayer and add a rule for delete_implementation_item: 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 Tickr. Nothing to install.
delete_implementation_item 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_implementation_item 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_implementation_item. 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_implementation_item is provided by the Tickr MCP server (@k-system/tickr-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 →