记录用户对思维模型使用体验的反馈
AI agents use record-user-feedback 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 writes/stores user feedback data. It creates a new record in a data store, which is a reversible write operation. The blast radius is low since it only records feedback and does not modify core system data or trigger significant side effects.
From the tool's definition 记录用户对思维模型使用体验的反馈 (Record user feedback on thinking model usage experience)
Documented attack patterns abuse exactly the kind of access record-user-feedback 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 record-user-feedback:
{
"version": "1",
"default": "deny",
"tools": {
"record-user-feedback": {
"limits": [
{
"counter": "record-user-feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}record-user-feedback 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.
记录用户对思维模型使用体验的反馈. 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 record-user-feedback: 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.
record-user-feedback 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 record-user-feedback 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 record-user-feedback. 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.
record-user-feedback 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.