report_usage · Agent-hive MCP: Risk & Policy

WHAT IT DOES

What report_usage does on Agent-hive

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

WHY IT NEEDS A POLICY

Why report_usage needs a policy

This tool creates or modifies feedback/usage records in the knowledge graph. While non-destructive, it writes data to the system and could influence node rankings, visibility, or auto-provisioning decisions if an agent submits false usage reports at scale.

From the tool's definition Tool description states 'Report whether a knowledge node was helpful after you used it' and 'Helps the hive learn which nodes are valuable.' The verb 'report' combined with context of recording feedback indicates data modification/creation (writing usage…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_usage Rate-limited

report_usage 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": {
    "report_usage": {
      "limits": [
        {
          "counter": "report_usage_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-hive, so you can run agents against it safely.

FAQ

Questions about report_usage

What does the report_usage tool do? +

Report whether a knowledge node was helpful after you used it. Helps the hive learn which nodes are valuable. It is categorised as a Write tool in the Agent-hive MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on report_usage? +

Register the Agent-hive MCP server in PolicyLayer and add a rule for report_usage: 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-hive. Nothing to install.

What risk level is report_usage? +

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

Can I rate-limit report_usage? +

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

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

report_usage is provided by the Agent-hive MCP server (kelvinyuefanli/agent-hive). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.