get-customers
AI agents call get-customers 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 'get-customers' tool retrieves or queries customer data from a Shopify store with no side effects or modifications. This is a Read operation. Severity is medium because customer data includes PII (names, emails, addresses, purchase history) that could be exposed if an agent is compromised or tricked into exfiltrating it at scale, though the tool itself is not destructive or financial.
From the tool's definition Tool named 'get-customers' on a Shopify MCP server that enables interaction with store data; the naming convention ('get-') and sibling context (create-customer, create-draft-order, etc.) indicate this retrieves customer data without modifying it.
Attacks that exploit this kind of access
get-customers. 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-customers: 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-customers 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-customers 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-customers. 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-customers 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 →