Purpose-built analytics over Pancake POS orders. Single call, no pagination, no client-side aggregation. USE THIS FOR: top-N orders, revenue/total queries. Actions: - top_orders: Find top N orders by metric (total_price | total_quantity). Optional date range + status filter. Thin response with id...
AI agents call analytics to retrieve information from Pancake Pos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though analytics only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Documented attack patterns abuse exactly the kind of access analytics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pancake Pos, and nothing reaches the server without passing your rules. This is the rule we recommend for analytics:
{
"version": "1",
"default": "deny",
"tools": {
"analytics": {}
}
}analytics 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.
Purpose-built analytics over Pancake POS orders. Single call, no pagination, no client-side aggregation. USE THIS FOR: top-N orders, revenue/total queries. Actions: - top_orders: Find top N orders by metric (total_price | total_quantity). Optional date range + status filter. Thin response with id/total_price/inserted_at/customer name. - revenue_summary: Revenue + count + status breakdown for a date range using server-side Elasticsearch aggregations. Returns revenue_cod (cash-on-delivery), prepaid, shipping_fee, partner_fee, total_orders, status_breakdown. Currency: VND. Examples: - Top 5 orders by total this year: analytics({ action:. It is categorised as a Read tool in the Pancake Pos MCP Server, which means it retrieves data without modifying state.
Register the Pancake Pos MCP server in PolicyLayer and add a rule for analytics: 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 Pancake Pos. Nothing to install.
analytics 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 analytics 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 analytics. 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.
analytics is provided by the Pancake Pos MCP server (nguyennguyenit/pancake-pos-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 24 Pancake Pos tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
24 Pancake Pos tools catalogued and risk-classified — across an index of 42,500+ MCP servers.