memory_feedback · Zhiyi MCP: Risk & Policy

WHAT IT DOES

What memory_feedback does on Zhiyi

AI agents use memory_feedback to create or update resources in Zhiyi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zhiyi environment.

PARAMETERS

Parameter	Type	Required	Description
`comment`	string	—
`sessionId`	string	—	Recall 会话 ID
`knowledgeId`	number	Yes	知识 ID
`feedbackType`	string	Yes

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why memory_feedback needs a policy

This tool submits feedback on memory recall results, which is a write operation (creating/modifying feedback data). It does not appear to delete data or execute code. Confidence is moderate because the description is brief and in Chinese, but the intent is clearly to post feedback data reversibly.

From the tool's definition 对 Recall 结果提交效果反馈 (Submit feedback on Recall results)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_feedback Rate-limited

memory_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "memory_feedback": {
      "limits": [
        {
          "counter": "memory_feedback_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Zhiyi, so you can run agents against it safely.

FAQ

Questions about memory_feedback

What does the memory_feedback tool do? +

对 Recall 结果提交效果反馈. It is categorised as a Write tool in the Zhiyi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does memory_feedback accept? +

memory_feedback accepts 4 parameters: comment, sessionId, knowledgeId, feedbackType. Required: knowledgeId, feedbackType. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on memory_feedback? +

Register the Zhiyi MCP server in PolicyLayer and add a rule for memory_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 Zhiyi. Nothing to install.

What risk level is memory_feedback? +

memory_feedback is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit memory_feedback? +

Yes. Add a rate_limit block to the memory_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.

How do I block memory_feedback completely? +

Set action: deny in the PolicyLayer policy for memory_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.

What MCP server provides memory_feedback? +

memory_feedback is provided by the Zhiyi MCP server (zhiyi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.