AI agents use patch_fee 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.
This tool modifies financial records (fee entry states) within a law firm practice management system, but does not move money or create new financial obligations—it toggles existing fee attributes between billable/billed states. This is Write (reversible modification) rather than Financial (which involves actual money movement) or Destructive (which cannot be undone).
From the tool's definition Tool name 'patch_fee' and description 'Toggle a fee entry's billable or billed state (PATCH)' indicates modification of billing/fee data. The PATCH HTTP method confirms it modifies existing data.
Attacks that exploit this kind of access
Toggle a fee entry's billable or billed state (PATCH). Use 'true' or 'false'. 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.
Register the Smokeball MCP server in PolicyLayer and add a rule for patch_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.
patch_fee is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the patch_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 patch_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.
patch_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 →