交互式推理过程，允许动态获取额外信息
AI agents invoke interactive-reasoning to trigger actions in Tianji. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool runs an interactive reasoning process that dynamically retrieves or fetches additional information during execution. This constitutes an active execution of a reasoning/inference pipeline with dynamic external information acquisition, placing it in the Execute category. The description is in Chinese and somewhat vague about the exact operations performed, reducing confidence slightly.
From the tool's definition '交互式推理过程，允许动态获取额外信息' — 'interactive reasoning process, allows dynamically obtaining additional information'
Documented attack patterns abuse exactly the kind of access interactive-reasoning 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 interactive-reasoning:
{
"version": "1",
"default": "deny",
"tools": {
"interactive-reasoning": {
"limits": [
{
"counter": "interactive-reasoning_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}interactive-reasoning stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
交互式推理过程，允许动态获取额外信息. It is categorised as a Execute tool in the Tianji MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tianji MCP server in PolicyLayer and add a rule for interactive-reasoning: 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.
interactive-reasoning is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the interactive-reasoning 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 interactive-reasoning. 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.
interactive-reasoning 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.