report_outcome · Agent-hive MCP: Risk & Policy

WHAT IT DOES

What report_outcome does on Agent-hive

AI agents use report_outcome 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_outcome needs a policy

This tool creates or modifies data records in the shared knowledge graph by logging outcomes and success signals. It does not execute external code, delete irreversibly, or move money. The Write category is appropriate because it contributes to the graph's state in a reversible manner (outcomes can be updated or corrected).

From the tool's definition Tool description states 'Report the outcome of an action' and 'Helps the hive learn which approaches succeed,' indicating it creates or modifies data (outcome records) in the knowledge graph.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_outcome Rate-limited

report_outcome 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_outcome": {
      "limits": [
        {
          "counter": "report_outcome_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_outcome

What does the report_outcome tool do? +

Report the outcome of an action — what you tried and whether it worked. Helps the hive learn which approaches succeed. 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_outcome? +

Register the Agent-hive MCP server in PolicyLayer and add a rule for report_outcome: 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_outcome? +

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

Can I rate-limit report_outcome? +

Yes. Add a rate_limit block to the report_outcome 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_outcome completely? +

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

report_outcome 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.