AI agents call find_best_store_for_item to retrieve information from Ikea without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries inventory data across store locations without modifying, creating, deleting, or executing any operations. It is a read-only lookup function consistent with the server's stated purpose. The low severity reflects minimal blast radius—returning stock information poses no operational risk.
From the tool's definition Tool description states it 'Find stores with the highest in-stock quantity for an item' and 'Returns' results. The server is explicitly described as 'Read-only' for 'product search and in-store stock lookup'.
Attacks that exploit this kind of access
Find stores with the highest in-stock quantity for an item. Returns up to maxResults stores sorted by quantity descending. Optionally filter by countryCode (. It is categorised as a Read tool in the Ikea MCP Server, which means it retrieves data without modifying state.
Register the Ikea MCP server in PolicyLayer and add a rule for find_best_store_for_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 Ikea. Nothing to install.
find_best_store_for_item 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 find_best_store_for_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 find_best_store_for_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.
find_best_store_for_item is provided by the Ikea MCP server (taejin5314/ikea-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 →