Delete a fee entry by ID.
AI agents call delete_fee to permanently remove resources in Smokeball — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting fee entries is destructive because it irreversibly removes billing records that are critical to law firm financial operations and client billing. This action cannot be undone and could result in loss of billing data, audit trail gaps, and financial reconciliation issues. While related to financial systems, the destructive nature of permanent deletion makes it more severe than a Write operation.
From the tool's definition Tool name 'delete_fee' with description 'Delete a fee entry by ID' explicitly performs deletion of billing/financial records, which is irreversible.
Attacks that exploit this kind of access
Delete a fee entry by ID. It is categorised as a Destructive tool in the Smokeball MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Smokeball MCP server in PolicyLayer and add a rule for delete_fee: 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.
delete_fee is a Destructive 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 delete_fee 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 delete_fee. 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.
delete_fee 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 →