Forecast demand by product, collection, or SKU using TimesFM 2.5.
AI agents call forecast_demand 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 is a read-only analytical tool that retrieves insights and predictions from existing data. It queries historical demand data to generate forecasts but does not create, modify, delete, or execute any actions on the Shopify store. Forecasting is inherently a non-destructive analysis operation with no irreversible consequences or financial transactions.
From the tool's definition Tool performs forecasting/prediction analysis using TimesFM model on historical data. Description states 'Forecast demand' with no mention of creating orders, modifying inventory, executing transactions, or making any changes to the Shopify store.
Attacks that exploit this kind of access
Forecast demand by product, collection, or SKU using TimesFM 2.5. 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 forecast_demand: 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.
forecast_demand 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 forecast_demand 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 forecast_demand. 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.
forecast_demand 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 →