set_customer
AI agents use set_customer to create or update resources in AdminAgent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AdminAgent environment.
Without a description, we infer from context: 'set_customer' most likely creates or modifies customer records in Shopify, a reversible Write operation. The high severity reflects potential for misuse (e.g., modifying customer details, creating fake accounts, or altering customer relationships), though the empty description reduces confidence.
From the tool's definition Tool name is 'set_customer' with empty description; sibling tools on this Shopify Admin server include customer-affecting operations like 'cancel_order' and 'capture_payment', indicating this server manages customer data.
Attacks that exploit this kind of access
set_customer. It is categorised as a Write tool in the AdminAgent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AdminAgent MCP server in PolicyLayer and add a rule for set_customer: 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.
set_customer is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_customer 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 set_customer. 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.
set_customer 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 →