数据指标报表的查询条件助手。在调用 count_all_statement 导出报表前，使用此工具逐步获取可选的查询条件值。 ⚠️ get_branches 使用规范： - 用户说"所有城市"/"全部城市" → 不传 preset 和 keyword，返回 ERP 全量城市列表 - 用户指定具体直营城市名（如"广州""南宁"）→ 传 preset="直营"，从返回的直营城市中匹配 - keyword 仅用于非直营城市或探索性搜索，返回多条相似结果时必须让用户确认 支持的 action: - "get_branches" → 获取城市公司列表（不传参=全量，preset="直营"=仅直营城...
Part of the Yjzf server.
Free to start. No card required.
AI agents call statement_query to retrieve information from Yjzf without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though statement_query only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"statement_query": {}
}
}See the full Yjzf policy for all 16 tools.
These attack patterns abuse exactly the kind of access statement_query gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
数据指标报表的查询条件助手。在调用 count_all_statement 导出报表前，使用此工具逐步获取可选的查询条件值。 ⚠️ get_branches 使用规范： - 用户说"所有城市"/"全部城市" → 不传 preset 和 keyword，返回 ERP 全量城市列表 - 用户指定具体直营城市名（如"广州""南宁"）→ 传 preset="直营"，从返回的直营城市中匹配 - keyword 仅用于非直营城市或探索性搜索，返回多条相似结果时必须让用户确认 支持的 action: - "get_branches" → 获取城市公司列表（不传参=全量，preset="直营"=仅直营城市，keyword=模糊搜索） - "get_hierarchies" → 获取营销线层级选项（需传 branchIds。仅营销线层级维度(7)时使用） - "get_store_managers" → 根据层级获取管理人员列表（需传 branchIds + bizlineIds。仅营销线层级维度(7)时使用） - "get_statistics_targets" → 获取统计指标（不传 topName 返回22个大类名称；传 topName 返回该类下完整指标明细。需传 statisticsScope 指定维度） - "get_query_guide" → 获取各统计维度所需条件的依赖关系和调用顺序说明 - "get_districts" → 获取行政区列表（需传 branchIds 且长度必须为1。仅 scope=52/53 时使用，作为可选筛选条件） - "get_trading_areas" → 获取商圈列表（需传 branchIds + districtCodes。仅 scope=53 时使用，作为可选筛选条件） - "get_sub_branches" → 获取子公司列表（需传 branchIds 且长度必须为1。仅 scope=17 时使用，作为可选筛选条件） 典型调用顺序： 1. get_query_guide → 了解维度与条件的依赖关系 2. get_branches → 确定城市公司（全部城市不传参；指定直营城市传 preset="直营"） 3. get_statistics_targets → 先获取大类列表 → 再传 topName 获取具体指标 4. 若维度=7: get_hierarchies → 获取营销线层级 → get_store_managers → 获取管理人员 5. 若维度=52/53: get_districts → 获取行政区列表（可选筛选） 6. 若维度=53: get_trading_areas → 获取商圈列表（可选筛选） 7. 若维度=17: get_sub_branches → 获取子公司列表（可选筛选） 8. 条件收集完毕后调用 count_all_statement 导出. It is categorised as a Read tool in the Yjzf MCP Server, which means it retrieves data without modifying state.
Register the Yjzf MCP server in PolicyLayer and add a rule for statement_query: 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.
statement_query 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 statement_query 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 statement_query. 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.
statement_query 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.
Deterministic rules across all 16 Yjzf tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.