AI agents use op_create_item to create or update resources in Op — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Op environment.
op_create_item creates new password vault entries. This is a Write operation (reversible via deletion or editing) rather than Read (no retrieval), Execute (no command execution), or Destructive (creation is reversible). However, severity is high because misuse could add malicious credentials, backdoor accounts, or spam the vault with fake secrets that could be retrieved and used by an attacker.
From the tool's definition Server description states it 'enables MCP clients like Claude and Cursor to read, create, edit, and delete password vault items.' The tool name 'op_create_item' matches the 'create' operation.
Attacks that exploit this kind of access
op_create_item. It is categorised as a Write tool in the Op MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Op MCP server in PolicyLayer and add a rule for op_create_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_create_item 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 op_create_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_create_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_create_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 →