get-products
AI agents call get-products to retrieve information from Shopify MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'get-products' and its placement among write/destructive sibling tools (create-product, delete-product-image, etc.) indicates this retrieves product data without modification. Despite the empty description, the verb 'get' is unambiguously a read operation. Blast radius is minimal—querying product data poses no direct harm to the store's data integrity or business operations.
From the tool's definition Tool name 'get-products' combined with server context describing 'retrieval' of store data via GraphQL Admin API. Sibling tools include create, delete, and update operations, positioning this as a read-only query operation.
Attacks that exploit this kind of access
get-products. It is categorised as a Read tool in the Shopify MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Shopify MCP Server MCP server in PolicyLayer and add a rule for get-products: 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 MCP Server. Nothing to install.
get-products 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 get-products 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 get-products. 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.
get-products is provided by the Shopify MCP Server MCP server (tzenderman/shopify-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 →