AI agents call calculate_tip to retrieve information from Demo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a local calculation of tip and total bill amounts. It does not move money, create records, or interact with any external financial systems. It is essentially a read/compute operation that returns a derived value from inputs, similar to a calculator function. No data is written or deleted.
From the tool's definition 'Calculate tip amount and total bill' — this is a pure arithmetic/calculation function with no side effects, data modification, or financial transactions
Documented attack patterns abuse exactly the kind of access calculate_tip gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Demo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for calculate_tip:
{
"version": "1",
"default": "deny",
"tools": {
"calculate_tip": {}
}
}calculate_tip 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.
Calculate tip amount and total bill. It is categorised as a Read tool in the Demo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Demo MCP Server MCP server in PolicyLayer and add a rule for calculate_tip: 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 Demo MCP Server. Nothing to install.
calculate_tip 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 calculate_tip 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 calculate_tip. 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.
calculate_tip is provided by the Demo MCP Server MCP server (thechandanbhagat/mcp-demo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Demo MCP Server, 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.
3 Demo MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.