rc_add_causal_link · Rootcause MCP: Risk & Policy

WHAT IT DOES

What rc_add_causal_link does on Rootcause

AI agents use rc_add_causal_link 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_causal_link needs a policy

This tool creates new causal relationships within a structured root cause analysis model. While it modifies the analysis structure, the action is reversible (links can be removed or modified), making it a Write operation rather than Destructive or Execute.

From the tool's definition Tool description states it will 'Add a directed or bidirectional causal relationship between Why nodes', which creates/modifies data (causal links) in the root cause analysis structure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rc_add_causal_link Rate-limited

rc_add_causal_link 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_causal_link": {
      "limits": [
        {
          "counter": "rc_add_causal_link_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_causal_link

What does the rc_add_causal_link tool do? +

Add a directed or bidirectional causal relationship between Why nodes. 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_causal_link? +

Register the Rootcause MCP server in PolicyLayer and add a rule for rc_add_causal_link: 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_causal_link? +

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

Can I rate-limit rc_add_causal_link? +

Yes. Add a rate_limit block to the rc_add_causal_link 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_causal_link completely? +

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

rc_add_causal_link 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.