rc_build_teaching_case · Rootcause MCP: Risk & Policy

WHAT IT DOES

What rc_build_teaching_case does on Rootcause

AI agents use rc_build_teaching_case 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_build_teaching_case needs a policy

This tool creates a new artifact (a lesson plan) derived from existing data (a Why Tree). It produces a new structured document, which is a Write operation — creating/generating content. It does not execute code, delete data, or involve financial transactions. Misuse risk is medium since it produces educational content that could be misleading if based on flawed analysis, but has limited blast radius.

From the tool's definition Transform a completed Why Tree into a teaching-ready lesson plan

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rc_build_teaching_case Rate-limited

rc_build_teaching_case 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_build_teaching_case": {
      "limits": [
        {
          "counter": "rc_build_teaching_case_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_build_teaching_case

What does the rc_build_teaching_case tool do? +

Transform a completed Why Tree into a teaching-ready lesson plan. 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_build_teaching_case? +

Register the Rootcause MCP server in PolicyLayer and add a rule for rc_build_teaching_case: 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_build_teaching_case? +

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

Can I rate-limit rc_build_teaching_case? +

Yes. Add a rate_limit block to the rc_build_teaching_case 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_build_teaching_case completely? +

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

rc_build_teaching_case 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.