Search item overviews by title/tags/category. If no vault is provided, the server searches every visible vault client-side.
AI agents call item_search to retrieve information from Mcp 1password without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
item_search performs data retrieval with no side effects. It queries vault items and returns matching results without creating, modifying, deleting, or destructively altering any data. The blast radius of misuse is minimal—an agent could only retrieve item metadata it shouldn't access, not compromise vault contents or perform unauthorized actions. This is a classic Read category operation.
From the tool's definition Tool description states 'Search item overviews' - a query operation. The tool retrieves or lists items based on search criteria (title/tags/category) without modifying, deleting, or executing operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Search item overviews by title/tags/category. If no vault is provided, the server searches every visible vault client-side. It is categorised as a Read tool in the Mcp 1password MCP Server, which means it retrieves data without modifying state.
Register the Mcp 1password MCP server in PolicyLayer and add a rule for item_search: 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_search 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 item_search 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_search. 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_search 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 →