Delete a task by ID (v1 API).
AI agents call deleteTaskV1 to permanently remove resources in Lofty MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes a task from the system with no undo mechanism. While the blast radius is limited to a single task record (not system-wide), deletion is irreversible and represents data loss. This justifies Destructive classification and high severity. Confidence is high because the intent is unambiguous from both name and description.
From the tool's definition Tool name contains 'delete' and description states 'Delete a task by ID' — this is an irreversible removal of data.
Attacks that exploit this kind of access
Delete a task by ID (v1 API). It is categorised as a Destructive tool in the Lofty MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lofty MCP Server MCP server in PolicyLayer and add a rule for deleteTaskV1: 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 Lofty MCP Server. Nothing to install.
deleteTaskV1 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 deleteTaskV1 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 deleteTaskV1. 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.
deleteTaskV1 is provided by the Lofty MCP Server MCP server (nerdsnipe-inc/lofty-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 →