Create an item in a vault.
AI agents use item_create to create or update resources in Mcp 1password — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp 1password environment.
Creating items in a password manager vault is a Write operation—it modifies vault state reversibly. Severity is high because creating malicious items (fake credentials, phishing links, etc.) could compromise security practices or deceive users, but it is not Destructive (reversible) or Financial (no direct money movement). The 1Password context and presence of item_delete/item_archive siblings confirm reversibility.
From the tool's definition Tool name 'item_create' and description 'Create an item in a vault' indicate the tool creates data in 1Password vaults. This is reversible via item_delete or item_archive.
Attacks that exploit this kind of access
Create an item in a vault. It is categorised as a Write tool in the Mcp 1password MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp 1password MCP server in PolicyLayer and add a rule for item_create: 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_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the item_create 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_create. 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_create 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 →