AI agents invoke sell_lemonade to trigger actions in Lemonade Stand MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a business simulation action with side effects (inventory changes, revenue generation, game state progression) that cannot be predicted in advance and depend on dynamic factors like weather and pricing. It is not a simple Read (no side effects), Write (reversible data modification), Destructive (permanent deletion), or Financial (real money).
From the tool's definition The tool 'sell_lemonade' with description 'Open for business and see today' executes a game action that triggers the lemonade stand's daily sales simulation.
Documented attack patterns abuse exactly the kind of access sell_lemonade gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lemonade Stand MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for sell_lemonade:
{
"version": "1",
"default": "deny",
"tools": {
"sell_lemonade": {
"limits": [
{
"counter": "sell_lemonade_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}sell_lemonade stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open for business and see today. It is categorised as a Execute tool in the Lemonade Stand MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Lemonade Stand MCP Server MCP server in PolicyLayer and add a rule for sell_lemonade: 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 Lemonade Stand MCP Server. Nothing to install.
sell_lemonade is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sell_lemonade 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 sell_lemonade. 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.
sell_lemonade is provided by the Lemonade Stand MCP Server MCP server (jimmcq/lemonade-stand-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lemonade Stand 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.
5 Lemonade Stand MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.