AI agents call list_categories 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 tool retrieves and lists metadata about available service categories on the platform. It is a read-only query operation with no side effects, data modification, code execution, or financial implications. The low severity reflects minimal risk even if misused—an AI agent listing categories cannot harm system integrity or user data.
From the tool's definition Tool name 'list_categories' and description indicate querying/listing service categories and subcategories ('查询即时财税平台支持的所有服务品类及子分类' = 'query all supported service categories and subcategories on the instant finance-tax platform').
Attacks that exploit this kind of access
查询即时财税平台支持的所有服务品类及子分类。适用场景：外部 AI 需要了解平台服务范围时调用。. 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 list_categories: 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.
list_categories 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 list_categories 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 list_categories. 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.
list_categories 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 →