This record as markdown: /tools/andyleimc-source-tencent-ad-mcp/categories-attribute-get.md
What categories_attribute_get does on Tencent Ad MCP Server
AI agents call categories_attribute_get to retrieve information from Tencent Ad MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why categories_attribute_get is rated Low
This tool queries or retrieves product category attributes without side effects. It follows the 'get' pattern consistent with other read operations on the server (ad_label_get, ad_param_get, adgroup_negativewords_get). No data is modified, deleted, or executed—only retrieved. Severity is low because unauthorized access to product attributes poses minimal risk compared to account compromise or financial operations.
From the tool's definition Tool name 'categories_attribute_get' and description '获取商品属性' (get product attributes) indicate a retrieval operation. The '_get' suffix and lack of any modification, deletion, or execution keywords confirm read-only behavior.
Attacks that exploit this kind of access
The rule that runs categories_attribute_get safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Tencent Ad MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For categories_attribute_get, this is the rule to start with:
categories_attribute_get is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Tencent Ad MCP Server, apply this rule, and every categories_attribute_get call is checked against it from then on.
Questions about categories_attribute_get
获取商品属性. It is categorised as a Read tool in the Tencent Ad MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tencent Ad MCP Server MCP server in PolicyLayer and add a rule for categories_attribute_get: 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 Tencent Ad MCP Server. Nothing to install.
categories_attribute_get 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 categories_attribute_get 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 categories_attribute_get. 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.
categories_attribute_get is provided by the Tencent Ad MCP Server MCP server (andyleimc-source/tencent-ad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Tencent Ad MCP Server, and thousands of servers like it.
This server
Across the catalogue