AI agents call new_house_competitor_data_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 |
|---|---|---|---|
action | string | Yes | 要执行的动作：get_competitors=获取竞对列表，export=执行导出 |
brandId | string | Yes | 品牌ID，必须通过 brand_select 工具获取，禁止自行编造 |
endTime | number | — | 统计结束时间(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 23:59:59.999 |
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 |
startTime | number | — | 统计开始时间(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 00:00:00 |
branchName | string | Yes | 城市公司名称，必须通过 branch_select 工具获取，用于文件命名 |
dimensionType | string | — | 统计维度：department=按部门统计(默认), projectManager=按项目负责人统计, onSite=按驻场统计 |
competitorList | array | — | 竞对ID列表（必填，1~10个），必须传 get_competitors 返回的 val 字段值，禁止传中文名称(name) |
Parameters from the server's own tool schema.
This tool reads and exports competitive analysis data from an ERP system into an Excel file. It retrieves/queries data (competitor lists and comparison data) without modifying or deleting anything. The async export pattern (submit task → poll status → download file) is still fundamentally a read/export operation. Severity is medium because it exports potentially sensitive competitive business data from an ERP system.
From the tool's definition 导出新房竞对对比数据，生成Excel文件 (exports new house competitor comparison data, generates Excel file)
Attacks that exploit this kind of access
从ERP系统导出新房竞对对比数据，生成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: get_competitors获取竞对列表, export执行导出（异步模式：提交任务→轮询状态→下载文件）。. It is categorised as a Read tool in the Yjzf MCP Server, which means it retrieves data without modifying state.
new_house_competitor_data_export accepts 9 parameters: action, brandId, endTime, branchId, cityCode, startTime, branchName, dimensionType, competitorList. 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 new_house_competitor_data_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.
new_house_competitor_data_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 new_house_competitor_data_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 new_house_competitor_data_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.
new_house_competitor_data_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 →