AI agents call examine_payment 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：query=查询列表，export=异步导出 |
billNo | string | — | 发票号，可选 |
pageNo | number | — | 页码，仅 action=query 有效。不传默认 1 |
status | number | — | 回款状态，可选。枚举值：2=待审核，4=已拒绝，8=待入账，16=已回款，32=已作废，128=待开票 |
batchNo | string | — | 回款批次号，可选 |
brandId | string | Yes | 品牌ID，通过 branch_select 工具获取 |
orderNo | string | — | 订单编号，可选 |
bookName | string | — | 导出的文件名称，仅 action=export 有效。不传则自动生成 |
branchId | string | Yes | 城市公司ID，通过 branch_select 工具获取 |
custName | string | — | 客户姓名，可选 |
pageSize | number | — | 每页条数，仅 action=query 有效。不传默认 10 |
branchName | string | Yes | 城市公司名称，必须通过 branch_select 工具获取，禁止自行编造 |
Parameters from the server's own tool schema.
The tool's primary function is to query and export developer payment review batch data. While export operations move data, they do not modify, delete, or create records in the source system—they are read operations. The medium severity reflects that exported payment/financial data could be sensitive if exposed to unauthorized parties, but the tool itself performs no financial transactions.
From the tool's definition Tool description states two actions: 'query 查询批次列表' (query batch list) and 'export 异步导出批次明细' (asynchronously export batch details). Both operations retrieve or export data without modifying it.
Risk signalsHigh parameter count (18 properties)
Attacks that exploit this kind of access
查询或导出开发商回款审核批次数据。支持两个 action：query 查询批次列表，export 异步导出批次明细。branchId 和 brandId 必须通过 branch_select 工具获取，禁止自行编造。. It is categorised as a Read tool in the Yjzf MCP Server, which means it retrieves data without modifying state.
examine_payment accepts 12 parameters: action, billNo, pageNo, status, batchNo, brandId, orderNo, bookName, branchId, custName, pageSize, branchName. Required: action, brandId, branchId, 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 examine_payment: 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.
examine_payment 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 examine_payment 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 examine_payment. 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.
examine_payment 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 →