feedback_record · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What feedback_record does on Claude Flow

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

WHY IT NEEDS A POLICY

Why feedback_record needs a policy

The tool records feedback data, which is a write operation (creating/storing new records). It does not appear to delete, execute code, or handle finances. Severity is medium because misuse could corrupt or pollute learning/training data used by AI agents in this enterprise orchestration system, potentially degrading model behavior at scale.

From the tool's definition 'Record feedback for learning' — implies writing/storing feedback data persistently

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

feedback_record Rate-limited

feedback_record 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": {
    "feedback_record": {
      "limits": [
        {
          "counter": "feedback_record_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about feedback_record

What does the feedback_record tool do? +

Record feedback for learning. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on feedback_record? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for feedback_record: 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 Claude Flow. Nothing to install.

What risk level is feedback_record? +

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

Can I rate-limit feedback_record? +

Yes. Add a rate_limit block to the feedback_record 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 feedback_record completely? +

Set action: deny in the PolicyLayer policy for feedback_record. 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 feedback_record? +

feedback_record is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.