AI agents call search_services 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 queries service provider information from a platform based on filters (city, service type). It is purely informational with no side effects—no data is created, modified, deleted, or financial transactions executed. The blast radius of misuse is minimal as it only exposes read-only search and listing capabilities.
From the tool's definition Tool description indicates 'search' functionality that 'returns service provider lists containing name, rating, transaction volume, AI score'.
Attacks that exploit this kind of access
搜索即时财税平台上的企业服务商。支持按城市、服务类型筛选。返回服务商列表含名称、评分、成交量、AI评分。适用场景：用户想找代理记账、公司注册、商标注册等服务。. 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 search_services: 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.
search_services 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 search_services 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 search_services. 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.
search_services 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 →