unprotect_funds · Smokeball MCP: Risk & Policy

WHAT IT DOES

What unprotect_funds does on Smokeball

AI agents use unprotect_funds to commit financial operations through Smokeball — usually the final step of a payment, billing, or trading workflow. A call moves real money.

WHY IT NEEDS A POLICY

Why unprotect_funds needs a policy

This tool directly manipulates financial fund states by releasing reserved/protected funds back into available balances. In a law firm context, protected funds likely represent client trust accounts or escrow reserves, where improper release could constitute financial misconduct, breach of fiduciary duty, or misappropriation of client funds.

From the tool's definition Release protected (reserved) funds back to available balance

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

unprotect_funds Approval-gated

Any call to unprotect_funds is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "unprotect_funds": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE 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 unprotect_funds

What does the unprotect_funds tool do? +

Release protected (reserved) funds back to available balance. It is categorised as a Financial tool in the Smokeball MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on unprotect_funds? +

Register the Smokeball MCP server in PolicyLayer and add a rule for unprotect_funds: 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 unprotect_funds? +

unprotect_funds is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit unprotect_funds? +

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

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

unprotect_funds 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.