AI agents call check_reminders to retrieve information from Cn Funds without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though check_reminders 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.
Attacks that exploit this kind of access
检查是否有到期的提醒（AI 应在每次对话开始时主动调用此工具）。返回当前到期未触发的提醒列表，同一提醒每天只触发一次。. It is categorised as a Read tool in the Cn Funds MCP Server, which means it retrieves data without modifying state.
Register the Cn Funds MCP server in PolicyLayer and add a rule for check_reminders: 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 Cn Funds. Nothing to install.
check_reminders 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 check_reminders 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 check_reminders. 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.
check_reminders is provided by the Cn Funds MCP server (smallke/cn-funds-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.