创建新的思维模型并添加到系统中，用于填补知识缺口
AI agents use create-thinking-model to create or update resources in Tianji — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tianji environment.
This tool creates and stores new thinking models in a centralized repository. While the operation is reversible (models can presumably be deleted or modified), it modifies system state by adding new artifacts. This is a Write operation—not destructive since creation is reversible, not Execute since there is no arbitrary code execution or command invocation, and not Read since it changes rather than retrieves data.
From the tool's definition Tool name 'create-thinking-model' and description '创建新的思维模型并添加到系统中' (create new thinking model and add to system) indicate persistent creation of data within a structured system.
Documented attack patterns abuse exactly the kind of access create-thinking-model 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 create-thinking-model:
{
"version": "1",
"default": "deny",
"tools": {
"create-thinking-model": {
"limits": [
{
"counter": "create-thinking-model_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create-thinking-model stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
创建新的思维模型并添加到系统中，用于填补知识缺口. It is categorised as a Write tool in the Tianji MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tianji MCP server in PolicyLayer and add a rule for create-thinking-model: 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.
create-thinking-model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create-thinking-model 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 create-thinking-model. 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.
create-thinking-model 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.