task_delete
AI agents call task_delete to permanently remove resources in Task Crusader MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The 'delete' operation is inherently destructive as it irreversibly removes task data. While the blast radius is somewhat constrained to task records (not full system destruction or data across multiple campaigns), the permanent loss of task information and any associated metadata represents a high-severity destructive action that could compromise project tracking and audit trails.
From the tool's definition Tool name is 'task_delete' with no description provided. The verb 'delete' indicates irreversible removal of data. In a task management system, deleting a task removes it permanently and cannot be undone.
Attacks that exploit this kind of access
task_delete. It is categorised as a Destructive tool in the Task Crusader MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Task Crusader MCP server in PolicyLayer and add a rule for task_delete: 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 Task Crusader MCP. Nothing to install.
task_delete 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 task_delete 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 task_delete. 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.
task_delete is provided by the Task Crusader MCP server (mcrescenzo/task-crusader-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 →