AI agents call monthly_attendance_export 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 |
|---|---|---|---|
brandId | string | Yes | 品牌ID，必须通过 brand_select 工具获取，禁止自行编造 |
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 |
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 |
departments | array | — | 部门ID列表（选填，多选）。不传则导出全部部门 |
attendanceMonth | string | Yes | 考勤月份（格式 YYYY-MM，如 2026-06）。用户未指定时默认取本月。必须先调用 get_current_time 获取当前时间作为参考再计算，严禁自行估算。最早支持过去7个月含本月 |
includeResigned | boolean | — | 是否包含离职人员（选填）。不传或传 false 则不包含，传 true 则包含 |
attendanceGroups | array | — | 考勤组ID列表（选填，多选）。不传则导出全部考勤组 |
Parameters from the server's own tool schema.
The tool exports/reads attendance records into an Excel file. It retrieves existing HR data without modifying, deleting, or executing anything. However, severity is medium because the exported data contains sensitive employee PII (names, employee IDs, department info, attendance patterns) that could be misused if exfiltrated.
From the tool's definition 导出每月考勤明细Excel文件 (export monthly attendance detail Excel file) — retrieves attendance data including names, employee IDs, departments, attendance groups, shifts, months, attendance days, late/early/out/补卡, various leave types, absenteeism, overtime duration
Attacks that exploit this kind of access
导出每月考勤明细Excel文件。包含姓名、工号、部门、考勤组、班次、考勤月份、出勤天数、迟到/早退/外出/补卡、各类假期、旷工、加班时长等完整字段。必须先调用 brand_select 获取 brandId，再调用 branch_select 获取 branchId、cityCode 和 branchName。支持多城市逐一导出。. It is categorised as a Read tool in the Yjzf MCP Server, which means it retrieves data without modifying state.
monthly_attendance_export accepts 8 parameters: brandId, branchId, cityCode, branchName, departments, attendanceMonth, includeResigned, attendanceGroups. Required: brandId, branchId, cityCode, branchName, attendanceMonth. 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 monthly_attendance_export: 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.
monthly_attendance_export 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 monthly_attendance_export 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 monthly_attendance_export. 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.
monthly_attendance_export 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 →