AI agents call store_inspection to retrieve information from Yjzf without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
action | string | Yes | 要执行的动作 |
pageNo | number | — | 页码，仅 query 时使用，不传默认1 |
brandId | string | Yes | 品牌ID，必须通过 brand_select 工具获取，禁止自行编造 |
endTime | number | — | 巡店结束时间(毫秒时间戳)。用户有指定日期时，必须先调用 get_current_time 获取当前时间作为参考，再用 date_to_timestamp(endOfDay=true) 转换，严禁自行估算。不传默认今天结束。时间范围最长不超过365天,超出时提示用户缩短范围 |
branchId | string | Yes | 城市公司ID(即organId)，必须通过 branch_select 工具获取，禁止自行编造 |
cityCode | string | Yes | 城市编码，必须通过 branch_select 工具获取，禁止自行编造 |
pageSize | number | — | 每页条数，仅 query 时使用，不传默认10 |
startTime | number | — | 巡店开始时间(毫秒时间戳)。用户有指定日期时，必须先调用 get_current_time 获取当前时间作为参考，再用 date_to_timestamp 转换，严禁自行估算。不传默认本月第一天。时间范围最长不超过365天,超出时提示用户缩短范围 |
branchName | string | Yes | 城市公司名称（用于文件命名），必须通过 branch_select 工具获取，禁止自行编造 |
Parameters from the server's own tool schema.
This tool retrieves and exports store inspection records from an ERP system. While it supports both preview and export actions, both are read-only operations that retrieve historical data without modifying, deleting, or executing operations. The prerequisite calls to branch_select and brand_select are configuration steps for filtering.
From the tool's definition Tool performs queries and exports from ERP system: 'query预览数据, export执行导出' (query to preview data, export to perform export). Actions are limited to retrieving store inspection records as Excel files with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
从ERP系统查询/导出巡店记录Excel文件。必须先调用 brand_select 获取 brandId，再调用 branch_select 获取 branchId 和 cityCode。支持2个action: query预览数据, export执行导出。确认城市公司（必填，支持多选）、确认巡店日期（必填，默认本月含今天；单次最长365天，超出时提示用户缩短范围）。. It is categorised as a Read tool in the Yjzf MCP Server, which means it retrieves data without modifying state.
store_inspection accepts 9 parameters: action, pageNo, brandId, endTime, branchId, cityCode, pageSize, startTime, branchName. Required: action, brandId, branchId, cityCode, branchName. The full parameter table on this page comes from the server's own tool schema.
Register the Yjzf MCP server in PolicyLayer and add a rule for store_inspection: 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 Yjzf. Nothing to install.
store_inspection 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 store_inspection 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 store_inspection. 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.
store_inspection is provided by the Yjzf MCP server (@yjzf/mcp-server-yjzf). 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 →