AI agents call count-models 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 performs a read-only operation to retrieve a count of existing thinking models. It has no side effects, does not execute code, does not modify data, and does not create financial obligations. The operation is purely informational and returns statistical metadata about the server's model inventory.
From the tool's definition Tool name 'count-models' and description '统计当前思维模型的总数' (count the total number of current thinking models) indicates a query operation that retrieves aggregate statistics without modifying, executing, or deleting any data.
Documented attack patterns abuse exactly the kind of access count-models 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 count-models:
{
"version": "1",
"default": "deny",
"tools": {
"count-models": {}
}
}count-models 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.
统计当前思维模型的总数. 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 count-models: 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.
count-models 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 count-models 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 count-models. 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.
count-models 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.