AI agents call get_price_reference to retrieve information from Jishics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it retrieves pricing information and market data without modifying anything. However, severity is raised to 'medium' rather than 'low' because pricing information in a financial services context could be sensitive business intelligence, and an AI agent with unrestricted access could infer competitive strategies, client budgets, or market positioning.
From the tool's definition The tool description indicates it 'queries market price ranges and real quotation samples' (查询...市场价格区间和真实报价样本) for specified categories and cities. This is fundamentally a retrieval operation that returns pricing reference data.
Attacks that exploit this kind of access
查询指定品类在某城市的市场价格区间和真实报价样本。适用场景：外部 AI 估算服务成本和预算参考。. It is categorised as a Read tool in the Jishics MCP Server, which means it retrieves data without modifying state.
Register the Jishics MCP server in PolicyLayer and add a rule for get_price_reference: 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 Jishics. Nothing to install.
get_price_reference 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_price_reference 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_price_reference. 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_price_reference is provided by the Jishics MCP server (lpxuesir5555/jishics-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 →