AI agents call get_customer to retrieve information from Creem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation to fetch existing customer information. It has no side effects—no data is created, modified, deleted, or financial transactions are initiated. The retrieval of customer details is a standard Read operation with minimal security risk, appropriate for an AI agent to access customer records for legitimate business logic.
From the tool's definition Tool name 'get_customer' and description 'Retrieve customer details by email or customer ID' indicates a data retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Retrieve customer details by email or customer ID. It is categorised as a Read tool in the Creem MCP Server, which means it retrieves data without modifying state.
Register the Creem MCP server in PolicyLayer and add a rule for get_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 Creem. Nothing to install.
get_customer 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_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 get_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.
get_customer is provided by the Creem MCP server (selenium39/mcp-server-creem). 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 →