获取当前用户有权限的品牌列表（单选）。调用任何导出工具前，必须先调用此工具获取 brandId，再调用 branch_select 获取对应品牌下的城市公司，最后执行导出。如果返回结果包含 autoSelected: true 字段，表示已自动选择默认品牌，直接使用该 brandId 即可，无需向用户确认；availableBrands 字段包含所有可选品牌，用户可主动要求切换到其中的其他品牌。否则返回 [{ brandId, brandName }] 列表，请让用户选择。
AI agents call brand_select 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.
This tool retrieves a list of brands the current user has permission to access. It is a pure read/query operation with no side effects, used to obtain a brandId before subsequent export operations.
From the tool's definition 获取当前用户有权限的品牌列表（单选）
Attacks that exploit this kind of access
获取当前用户有权限的品牌列表（单选）。调用任何导出工具前，必须先调用此工具获取 brandId，再调用 branch_select 获取对应品牌下的城市公司，最后执行导出。如果返回结果包含 autoSelected: true 字段，表示已自动选择默认品牌，直接使用该 brandId 即可，无需向用户确认；availableBrands 字段包含所有可选品牌，用户可主动要求切换到其中的其他品牌。否则返回 [{ brandId, brandName }] 列表，请让用户选择。. 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 brand_select: 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.
brand_select 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 brand_select 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 brand_select. 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.
brand_select 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 →