解释模型的推理过程和应用的思维模式
AI agents call explain-reasoning-process 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 retrieves and explains reasoning processes and thinking patterns—it reads and returns information about model behavior without modifying, executing code, deleting data, or creating side effects. It is purely informational, placing it in the Read category with low severity since it cannot alter system state or be misused to cause harm.
From the tool's definition Tool name 'explain-reasoning-process' and description '解释模型的推理过程和应用的思维模式' (explain the model's reasoning process and applied thinking patterns) indicate a retrieval/query operation that returns information about how models reason.
Documented attack patterns abuse exactly the kind of access explain-reasoning-process 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 explain-reasoning-process:
{
"version": "1",
"default": "deny",
"tools": {
"explain-reasoning-process": {}
}
}explain-reasoning-process 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.
解释模型的推理过程和应用的思维模式. 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 explain-reasoning-process: 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.
explain-reasoning-process 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 explain-reasoning-process 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 explain-reasoning-process. 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.
explain-reasoning-process 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.