AI agents use create_transaction to commit financial operations through Smokeball — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly creates financial transactions in bank accounts, moving money by recording deposits or withdrawals. This falls squarely in the Financial category as it commits financial obligations and affects real monetary balances in a law firm's accounts (including potentially client trust accounts). Misuse could result in unauthorized financial movements, making severity critical.
From the tool's definition 'Create a bank account transaction. amount: positive for deposit, negative for withdrawal.'
Attacks that exploit this kind of access
Create a bank account transaction. amount: positive for deposit, negative for withdrawal. 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.
Register the Smokeball MCP server in PolicyLayer and add a rule for create_transaction: 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.
create_transaction is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the create_transaction 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.
Set action: deny in the PolicyLayer policy for create_transaction. 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.
create_transaction 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →