AI agents call get_cash_flow_data to retrieve information from A Share without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves financial data (cash flow statements) from a stock market database without modifying, deleting, or executing external operations. The 'get_' prefix and context of similar read-only tools on the server confirm Read classification. Severity is low because unauthorized access to historical stock data poses minimal risk—this information is typically public market data.
From the tool's definition Tool name 'get_cash_flow_data' contains the verb 'get', indicating data retrieval. Server description states it enables users to 'query Chinese A-share stock data, including stock basics, historical prices, financial reports, and macroeconomic indicators.'…
Attacks that exploit this kind of access
get_cash_flow_data. It is categorised as a Read tool in the A Share MCP Server, which means it retrieves data without modifying state.
Register the A Share MCP server in PolicyLayer and add a rule for get_cash_flow_data: 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 A Share. Nothing to install.
get_cash_flow_data 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 get_cash_flow_data 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 get_cash_flow_data. 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.
get_cash_flow_data is provided by the A Share MCP server (kissjerryfan/mcp_server). 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 →