AI agents call get_valuation_metrics 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 metrics and valuation indicators without modifying data, executing code, deleting records, or moving money. It performs a simple data query with no side effects, fitting squarely within the Read category. The low severity reflects minimal blast radius—misuse would only expose financial data already publicly available in stock market contexts.
From the tool's definition Tool name 'get_valuation_metrics' and description '获取股票的估值指标数据，包括市盈率(P/E)、市净率(P/B)、市销率(P/S)等的实时数据和历史趋势' (retrieves stock valuation metrics data including P/E, P/B, P/S ratios with real-time data and historical trends).
Attacks that exploit this kind of access
获取股票的估值指标数据，包括市盈率(P/E)、市净率(P/B)、市销率(P/S)等的实时数据和历史趋势。. 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_valuation_metrics: 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_valuation_metrics 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_valuation_metrics 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_valuation_metrics. 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_valuation_metrics 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 →