Execute a ShopifyQL query for analytics (requires read_analytics scope)
AI agents call shopifyql_query to retrieve information from Shopify Graphql 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 analytical data from Shopify without modifying, deleting, or executing operations that would cause side effects. The read_analytics scope explicitly restricts the tool to read operations. ShopifyQL queries for analytics are non-destructive data retrieval operations.
From the tool's definition Tool name 'shopifyql_query' and description states 'Execute a ShopifyQL query for analytics (requires read_analytics scope)' - the read_analytics scope and query execution for analytics purposes indicate data retrieval only.
Attacks that exploit this kind of access
Execute a ShopifyQL query for analytics (requires read_analytics scope). It is categorised as a Read tool in the Shopify Graphql MCP Server, which means it retrieves data without modifying state.
Register the Shopify Graphql MCP server in PolicyLayer and add a rule for shopifyql_query: 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 Graphql. Nothing to install.
shopifyql_query 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 shopifyql_query 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 shopifyql_query. 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.
shopifyql_query is provided by the Shopify Graphql MCP server (uvu-store/shopify-graphql-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 →