rc_add_cause · Rootcause MCP: Risk & Policy

WHAT IT DOES

What rc_add_cause does on Rootcause

AI agents use rc_add_cause 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_add_cause needs a policy

This tool modifies the state of a root cause analysis by adding causal data to a Fishbone diagram. While the operation is reversible (causes can presumably be removed or edited via rc_archive_session or similar), it creates/modifies structured analytical content used in medical education.

From the tool's definition Tool name 'rc_add_cause' and description 'Add a cause to a Fishbone category' indicate creation/modification of data within an analytical structure (Fishbone diagram). The 'Add' verb confirms a write operation that creates new causal entries.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rc_add_cause Rate-limited

rc_add_cause 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_add_cause": {
      "limits": [
        {
          "counter": "rc_add_cause_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_add_cause

What does the rc_add_cause tool do? +

Add a cause to a Fishbone category. 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_add_cause? +

Register the Rootcause MCP server in PolicyLayer and add a rule for rc_add_cause: 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_add_cause? +

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

Can I rate-limit rc_add_cause? +

Yes. Add a rate_limit block to the rc_add_cause 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_add_cause completely? +

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

rc_add_cause 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.