New vs returning customer metrics.
AI agents call customer_acquisition 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.
This tool reads and returns analytical metrics about customer acquisition patterns (new vs returning customers). It has no side effects, does not modify any data, and is purely a reporting/analytics function. Misuse potential is low as it only exposes aggregate customer metrics.
From the tool's definition 'New vs returning customer metrics' — purely retrieves and reports customer acquisition statistics
Attacks that exploit this kind of access
New vs returning customer metrics. 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 customer_acquisition: 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.
customer_acquisition 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 customer_acquisition 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 customer_acquisition. 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.
customer_acquisition 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 →