list_customers
AI agents call list_customers to retrieve information from AdminAgent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries customer data with no stated side effects. However, severity is elevated to 'medium' rather than 'low' because customer data is sensitive PII (personally identifiable information) in a commercial context; unauthorized access to a customer list could enable fraud, privacy violations, or competitive harm.
From the tool's definition Tool name 'list_customers' with verb 'list' indicates data retrieval. The sibling tools on AdminAgent (which manages store data including products, collections, analytics) confirm this is a Shopify Admin data access endpoint.
Attacks that exploit this kind of access
list_customers. It is categorised as a Read tool in the AdminAgent MCP Server, which means it retrieves data without modifying state.
Register the AdminAgent MCP server in PolicyLayer and add a rule for list_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 AdminAgent. Nothing to install.
list_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 list_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 list_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.
list_customers is provided by the AdminAgent MCP server (rushikeshmore/admin-agent). 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 →