item_delete

THE RISK

Critical Risk

Why item_delete needs a policy

Destructive operations that permanently erase data from credential vaults represent the highest security risk. An agent misusing this tool could irreversibly delete critical passwords, authentication tokens, or other sensitive items stored in 1Password, leading to complete loss of access to accounts and systems. The permanent nature and impossibility of recovery make this critical severity.

From the tool's definition Tool description explicitly states 'Permanently delete an item from a 1Password vault' and 'This action cannot be undone' — classic destructive operation. The tool name 'item_delete' also directly indicates deletion.

Documented attack patterns abuse exactly the kind of access item_delete gives an agent:

POLICY

How to control item_delete

PolicyLayer is an MCP gateway — it sits between your AI agents and 1password, and nothing reaches the server without passing your rules. This is the rule we recommend for item_delete:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "item_delete"
  ]
}

item_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register 1password — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More 1password tools

Write password_create Create a new password/login item in a 1Password vault with optional username, URL, tags, a Write password_generate Generate a cryptographically secure random password with configurable length and character Write password_generate_memorable Generate a memorable passphrase from random dictionary words with optional number and symb Write password_update Update (rotate) a password or concealed field on an existing 1Password item. If the target Read item_lookup Search for items within a 1Password vault by title substring. Returns item IDs, titles, ca Read password_read Retrieve a secret from 1Password using either a secret reference (op://vault/item/field) o Read vault_list List all 1Password vaults accessible to the service account. Returns vault IDs, names, des

All 8 1password tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in 1password → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about item_delete

What does the item_delete tool do? +

Permanently delete an item from a 1Password vault. This action cannot be undone. It is categorised as a Destructive tool in the 1password MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on item_delete? +

Register the 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 1password. Nothing to install.

What risk level is item_delete? +

item_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit item_delete? +

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.

How do I block item_delete completely? +

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.

What MCP server provides item_delete? +

item_delete is provided by the 1password MCP server (@takescake/1password-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every 1password tool call.

Start from 1password, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →