Remove a SINGLE task or project from OmniFocus. For removing 2+ items, use batch_remove_items instead (9x faster).
AI agents call remove_item to permanently remove resources in OmniFocus MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes tasks or projects from OmniFocus without reversibility. While a single item removal has lower blast radius than batch operations, any deletion operation is irreversible and constitutes a destructive action.
From the tool's definition Tool name is 'remove_item' and description states it will 'Remove a SINGLE task or project from OmniFocus.' The verb 'remove' combined with the context of task/project management indicates irreversible deletion of data.
Attacks that exploit this kind of access
Remove a SINGLE task or project from OmniFocus. For removing 2+ items, use batch_remove_items instead (9x faster). It is categorised as a Destructive tool in the OmniFocus MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the OmniFocus MCP Server MCP server in PolicyLayer and add a rule for remove_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 OmniFocus MCP Server. Nothing to install.
remove_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 remove_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 remove_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.
remove_item is provided by the OmniFocus MCP Server MCP server (mojenmojen/of-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 →