op_delete_item
AI agents call op_delete_item to permanently remove resources in Op — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of vault items in a password manager is a destructive action that cannot be undone. An AI agent with access to this tool could permanently erase critical secrets, authentication credentials, or other sensitive vault contents. The blast radius is critical because compromised or misused deletion could lead to loss of access to important systems and services.
From the tool's definition Tool name 'op_delete_item' combined with sibling tools that perform vault management (op_create_item, op_edit_item, op_get_item, op_list_items, op_list_vaults) and the server description stating it 'enables MCP clients like Claude and Cursor to read, create,…
Attacks that exploit this kind of access
op_delete_item. It is categorised as a Destructive tool in the Op MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Op MCP server in PolicyLayer and add a rule for op_delete_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 Op. Nothing to install.
op_delete_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 op_delete_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 op_delete_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.
op_delete_item is provided by the Op MCP server (jluckyiv/op-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 →