抛硬币，返回正面或反面
AI agents call flip_coin to retrieve information from MCP Lottery Demo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a random outcome (coin flip result) without creating, modifying, deleting, or executing any consequential operations. It is purely a read/query operation that returns data. The Chinese description '抛硬币，返回正面或反面' (flip coin, return heads or tails) confirms this is a simple random draw with no destructive or financial implications.
From the tool's definition Tool performs 'flip_coin' which returns heads or tails - a random selection with no side effects, no data modification, and no external state changes.
Attacks that exploit this kind of access
抛硬币，返回正面或反面. It is categorised as a Read tool in the MCP Lottery Demo MCP Server, which means it retrieves data without modifying state.
Register the MCP Lottery Demo MCP server in PolicyLayer and add a rule for flip_coin: 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 MCP Lottery Demo. Nothing to install.
flip_coin 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 flip_coin 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 flip_coin. 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.
flip_coin is provided by the MCP Lottery Demo MCP server (pmhw/mcpdemo). 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 →