Count total customers in the store, optionally filtered by creation date.
AI agents call count_customers to retrieve information from Sapo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves aggregate data (customer count) without creating, modifying, deleting, or executing any operations. It is a read-only query with minimal impact even if misused by an AI agent, as it only returns statistics about existing customers.
From the tool's definition Tool name is 'count_customers' and description states it 'Count total customers in the store, optionally filtered by creation date' — a pure query operation with no modifications or side effects.
Documented attack patterns abuse exactly the kind of access count_customers gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sapo, and nothing reaches the server without passing your rules. This is the rule we recommend for count_customers:
{
"version": "1",
"default": "deny",
"tools": {
"count_customers": {}
}
}count_customers is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Count total customers in the store, optionally filtered by creation date. It is categorised as a Read tool in the Sapo MCP Server, which means it retrieves data without modifying state.
Register the Sapo MCP server in PolicyLayer and add a rule for count_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 Sapo. Nothing to install.
count_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 count_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 count_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.
count_customers is provided by the Sapo MCP server (nguyennguyenit/sapo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sapo, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
93 Sapo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.