Compare two time periods across revenue, orders, units, AOV, discount rate, and units per order.
AI agents call compare_periods to retrieve information from Shopify Forecast without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing Shopify store data to generate comparative reports across time periods. It performs no writes, deletions, financial transactions, or code execution—it is purely a Read operation that queries and presents data.
From the tool's definition Tool is named 'compare_periods' and described as comparing two time periods across metrics (revenue, orders, units, AOV, discount rate, units per order).
Attacks that exploit this kind of access
Compare two time periods across revenue, orders, units, AOV, discount rate, and units per order. It is categorised as a Read tool in the Shopify Forecast MCP Server, which means it retrieves data without modifying state.
Register the Shopify Forecast MCP server in PolicyLayer and add a rule for compare_periods: 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 Shopify Forecast. Nothing to install.
compare_periods 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 compare_periods 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 compare_periods. 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.
compare_periods is provided by the Shopify Forecast MCP server (mcostigliola321/shopify-forecast-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 →