Delete an item. Requires a reason and destructive-action acknowledgement.
AI agents call item_delete to permanently remove resources in Mcp 1password — 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 secrets management system is irreversible and cannot be undone. Even with confirmation requirements in place, an AI agent manipulated into invoking this tool could permanently remove sensitive credentials, API keys, or other critical secrets from 1Password vaults, causing significant operational damage. This falls under the Destructive category as the highest applicable severity.
From the tool's definition Tool name is 'item_delete' and description states 'Delete an item.' This explicitly performs deletion, an irreversible operation.
Attacks that exploit this kind of access
Delete an item. Requires a reason and destructive-action acknowledgement. It is categorised as a Destructive tool in the Mcp 1password MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp 1password MCP server in PolicyLayer and add a rule for item_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 Mcp 1password. Nothing to install.
item_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 item_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 item_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.
item_delete is provided by the Mcp 1password MCP server (kefapps/onepassword-mcp-codex). 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 →