rc_confirm_classification · Rootcause MCP: Risk & Policy

WHAT IT DOES

What rc_confirm_classification does on Rootcause

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

WHY IT NEEDS A POLICY

Why rc_confirm_classification needs a policy

This tool modifies the state of an HFACS classification by marking/confirming it as correct, which is a reversible write operation. It does not delete data, execute code, or involve financial transactions. The blast radius is low since it only affects a classification label within a root cause analysis session.

From the tool's definition Confirm an HFACS classification as correct

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rc_confirm_classification Rate-limited

rc_confirm_classification 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": {
    "rc_confirm_classification": {
      "limits": [
        {
          "counter": "rc_confirm_classification_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 Rootcause, so you can run agents against it safely.

FAQ

Questions about rc_confirm_classification

What does the rc_confirm_classification tool do? +

Confirm an HFACS classification as correct. It is categorised as a Write tool in the Rootcause MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on rc_confirm_classification? +

Register the Rootcause MCP server in PolicyLayer and add a rule for rc_confirm_classification: 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 Rootcause. Nothing to install.

What risk level is rc_confirm_classification? +

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

Can I rate-limit rc_confirm_classification? +

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

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

rc_confirm_classification is provided by the Rootcause MCP server (u9401066/rootcause-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.