AI agents call op_list_items to retrieve information from Op without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although this is a read-only operation, the severity is elevated to 'high' because it retrieves sensitive password vault metadata and item information from 1Password, a credential management system. An AI agent with unrestricted access to this tool could enumerate all secrets in accessible vaults, revealing organizational security posture and sensitive asset inventory.
From the tool's definition op_list_items lists items in a 1Password vault with no modification capability. The tool name and description both indicate a read-only operation: 'List items'.
Attacks that exploit this kind of access
List items in a 1Password vault. It is categorised as a Read tool in the Op MCP Server, which means it retrieves data without modifying state.
Register the Op MCP server in PolicyLayer and add a rule for op_list_items: 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_list_items is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the op_list_items 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_list_items. 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_list_items 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 →