report_failure · Agent-hive MCP: Risk & Policy

WHAT IT DOES

What report_failure does on Agent-hive

AI agents use report_failure 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_failure needs a policy

This tool creates or appends failure records to a shared knowledge graph without deleting or irreversibly overwriting data. While it affects shared state that other agents depend on, the write operation is reversible (records can be corrected or removed via edit_node or delete_node). Misuse could pollute the knowledge base with false failure reports, degrading agent decision-making, but the impact is correctable.

From the tool's definition Tool description states 'Report a failure' and indicates it records data ('so other agents can avoid it'), implying it creates or modifies entries in the shared knowledge graph.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_failure Rate-limited

report_failure 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_failure": {
      "limits": [
        {
          "counter": "report_failure_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_failure

What does the report_failure tool do? +

Report a failure (broken API, bad version, rate limit) so other agents can avoid it. The hive. 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_failure? +

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

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

Can I rate-limit report_failure? +

Yes. Add a rate_limit block to the report_failure 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_failure completely? +

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

report_failure 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.