AI agents call search_items to retrieve information from Rami Levy MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries product data from the grocery store catalog. It does not create, modify, delete, or execute any operations—it only returns search results. The blast radius of misuse is minimal; an agent could at most retrieve unwanted product information. This is clearly a Read operation.
From the tool's definition Tool name is 'search_items' and description states 'Search for items in the Rami Levy catalog'. The verb 'search' and the action of querying a catalog without modification are characteristic of retrieval operations with no side effects.
Documented attack patterns abuse exactly the kind of access search_items gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rami Levy MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_items:
{
"version": "1",
"default": "deny",
"tools": {
"search_items": {}
}
}search_items is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for items in the Rami Levy catalog. It is categorised as a Read tool in the Rami Levy MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Rami Levy MCP Server MCP server in PolicyLayer and add a rule for search_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 Rami Levy MCP Server. Nothing to install.
search_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 search_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 search_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.
search_items is provided by the Rami Levy MCP Server MCP server (shilomagen/rami-levy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rami Levy MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Rami Levy MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.