Delete a task from a project.
AI agents call task_delete to permanently remove resources in Recap — 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 record, which cannot be undone without external recovery mechanisms. This fits the Destructive category (irreversibly deletes data). Severity is high because an AI agent calling this with incorrect task identifiers could accidentally remove important project tasks, causing data loss and disruption to project management. Confidence is high based on explicit use of 'delete' language.
From the tool's definition Tool name is 'task_delete' and description states 'Delete a task from a project.' The verb 'delete' combined with the action of removing a task indicates irreversible data removal.
Attacks that exploit this kind of access
Delete a task from a project. It is categorised as a Destructive tool in the Recap MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Recap 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 Recap. 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 Recap MCP server (shivam-singh-git/recap-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 →