AI agents call get-categories to retrieve information from Tianji without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure retrieval operation that queries existing metadata about thinking model categories. It has no side effects, does not execute code or commands, does not modify or delete data, and does not involve financial transactions. The tool fits the 'Read' category as it simply fetches and returns information.
From the tool's definition Tool name 'get-categories' and description '获取所有思维模型的分类信息' (retrieve all thinking model classification information) indicate this retrieves or queries categorical metadata about thinking models.
Documented attack patterns abuse exactly the kind of access get-categories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tianji, and nothing reaches the server without passing your rules. This is the rule we recommend for get-categories:
{
"version": "1",
"default": "deny",
"tools": {
"get-categories": {}
}
}get-categories is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
获取所有思维模型的分类信息. It is categorised as a Read tool in the Tianji MCP Server, which means it retrieves data without modifying state.
Register the Tianji MCP server in PolicyLayer and add a rule for get-categories: 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 Tianji. Nothing to install.
get-categories 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 get-categories 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 get-categories. 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.
get-categories is provided by the Tianji MCP server (lanyijianke/thinking_models_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tianji, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 Tianji tools catalogued and risk-classified — across an index of 43,000+ MCP servers.