基于问题关键词推荐适合解决特定问题的思维模型
AI agents call recommend-models-for-problem 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 tool queries a knowledge base of thinking models and returns recommendations based on input keywords. It performs a search/lookup operation that retrieves and ranks information but does not create, modify, delete, execute code, or commit financial obligations. The operation is read-only with no persistence or external side effects.
From the tool's definition Tool name 'recommend-models-for-problem' and description '基于问题关键词推荐适合解决特定问题的思维模型' (recommend thinking models suitable for solving specific problems based on problem keywords) indicate data retrieval and recommendation functionality with no side effects.
Documented attack patterns abuse exactly the kind of access recommend-models-for-problem 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 recommend-models-for-problem:
{
"version": "1",
"default": "deny",
"tools": {
"recommend-models-for-problem": {}
}
}recommend-models-for-problem 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.
基于问题关键词推荐适合解决特定问题的思维模型. 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 recommend-models-for-problem: 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.
recommend-models-for-problem 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 recommend-models-for-problem 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 recommend-models-for-problem. 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.
recommend-models-for-problem 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.