Delete a task.
AI agents call delete_task to permanently remove resources in Mcp Google Tasks — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a task is an irreversible operation that destroys data without the possibility of automatic recovery through the same API. This makes it Destructive rather than Write. The severity is high because an AI agent could permanently remove user tasks if misdirected, though the blast radius is typically limited to individual task items rather than bulk data loss.
From the tool's definition Tool name is 'delete_task' and description states 'Delete a task.' The server description confirms this tool is part of task management capabilities that include 'delete tasks'.
Attacks that exploit this kind of access
Delete a task. It is categorised as a Destructive tool in the Mcp Google Tasks MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Google Tasks MCP server in PolicyLayer and add a rule for delete_task: 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 Mcp Google Tasks. Nothing to install.
delete_task 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_task 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_task. 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_task is provided by the Mcp Google Tasks MCP server (ktmage/mcp-google-tasks). 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 →