feedback_strategy · Agent-Comm-Hub MCP: Risk & Policy

WHAT IT DOES

What feedback_strategy does on Agent-Comm-Hub

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

WHY IT NEEDS A POLICY

Why feedback_strategy needs a policy

This tool creates or modifies feedback records in a multi-agent system. It is not destructive (feedback can be reconsidered or systems can evolve), not financial, and not execute-level (no code/command execution). The anti-spam constraint ('防刷' — one feedback per agent per strategy) confirms it manages mutable state.

From the tool's definition Tool description indicates it allows providing feedback (positive/negative/neutral) on strategies with one-feedback-per-agent-per-strategy enforcement.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

feedback_strategy Rate-limited

feedback_strategy 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_strategy": {
      "limits": [
        {
          "counter": "feedback_strategy_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 Agent-Comm-Hub, so you can run agents against it safely.

FAQ

Questions about feedback_strategy

What does the feedback_strategy tool do? +

对策略提供反馈（正面/负面/中性）。每个 Agent 对每个策略只能反馈一次（防刷）。. It is categorised as a Write tool in the Agent-Comm-Hub 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_strategy? +

Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for feedback_strategy: 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 Agent-Comm-Hub. Nothing to install.

What risk level is feedback_strategy? +

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

Can I rate-limit feedback_strategy? +

Yes. Add a rate_limit block to the feedback_strategy 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_strategy completely? +

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

feedback_strategy is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.