Check in-warehouse availability of a product at a specific Costco location
AI agents call check_warehouse_stock to retrieve information from Mcp Costco without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves product stock information without modifying any data, triggering transactions, or executing arbitrary commands. Even if an AI agent misuses it by querying exhaustively, the blast radius is minimal—it merely gathers existing inventory data. This is a straightforward Read operation.
From the tool's definition Tool description states it 'check[s]' warehouse availability, which is a read-only query operation with no side effects.
Attacks that exploit this kind of access
Check in-warehouse availability of a product at a specific Costco location. It is categorised as a Read tool in the Mcp Costco MCP Server, which means it retrieves data without modifying state.
Register the Mcp Costco MCP server in PolicyLayer and add a rule for check_warehouse_stock: 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 Costco. Nothing to install.
check_warehouse_stock 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 check_warehouse_stock 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 check_warehouse_stock. 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.
check_warehouse_stock is provided by the Mcp Costco MCP server (markswendsen-code/mcp-costco). 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 →