create_authorization_policy · Smokeball MCP: Risk & Policy

WHAT IT DOES

What create_authorization_policy does on Smokeball

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

WHY IT NEEDS A POLICY

Why create_authorization_policy needs a policy

This tool creates new authorization policies that control access to law firm data and systems. While creation is reversible (policies can typically be modified or deleted), this is a Write operation that establishes security controls. Severity is high because misconfigured authorization policies could expose sensitive client data, case files, and financial information.

From the tool's definition Tool creates an authorization policy with 'permissions_csv' parameter that defines access permissions. The description states 'Create an authorization policy' which is a creation operation that modifies system configuration.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_authorization_policy Rate-limited

create_authorization_policy 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": {
    "create_authorization_policy": {
      "limits": [
        {
          "counter": "create_authorization_policy_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 Smokeball, so you can run agents against it safely.

FAQ

Questions about create_authorization_policy

What does the create_authorization_policy tool do? +

Create an authorization policy. permissions_csv: comma-separated permission strings. It is categorised as a Write tool in the Smokeball MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_authorization_policy? +

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

What risk level is create_authorization_policy? +

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

Can I rate-limit create_authorization_policy? +

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

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

create_authorization_policy is provided by the Smokeball MCP server (rosenadvertising/smokeball-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.