scf_create_custom_risk · Scf MCP: Risk & Policy

WHAT IT DOES

What scf_create_custom_risk does on Scf

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

WHY IT NEEDS A POLICY

Why scf_create_custom_risk needs a policy

This tool creates new risk records in the compliance platform, which is a write operation. It generates organizational risk codes and associated assessment records. While write operations can have downstream consequences for compliance posture, the action itself is reversible (records can be updated or deleted), distinguishing it from destructive operations.

From the tool's definition Tool description explicitly states 'Create a custom org-defined risk (write — editor+ role)' and 'creates the matching risk assessment record.' The word 'Create' and the verb phrase 'creates the matching' indicate reversible data creation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scf_create_custom_risk Rate-limited

scf_create_custom_risk 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": {
    "scf_create_custom_risk": {
      "limits": [
        {
          "counter": "scf_create_custom_risk_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 Scf, so you can run agents against it safely.

FAQ

Questions about scf_create_custom_risk

What does the scf_create_custom_risk tool do? +

Create a custom org-defined risk (write — editor+ role). Auto-generates an R-ORG-N code and creates the matching risk assessment record. It is categorised as a Write tool in the Scf MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on scf_create_custom_risk? +

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

What risk level is scf_create_custom_risk? +

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

Can I rate-limit scf_create_custom_risk? +

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

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

scf_create_custom_risk is provided by the Scf MCP server (mcp-server-scf). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.