AI agents call list_fees to retrieve information from Smokeball without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries fee/billing data without creating, modifying, deleting, or executing any operations. It has no side effects on the underlying data. While fee information may be sensitive, the blast radius of misuse is limited to unauthorized data disclosure rather than financial transactions, data loss, or system compromise. Classified as Read with low severity.
From the tool's definition Tool description states 'List fee entries (billable time)' with optional filtering. The verb 'list' and the function of retrieving/querying existing fee data indicates a read-only operation with no modification or deletion capability.
Attacks that exploit this kind of access
List fee entries (billable time). Filter by matter_id for matter-specific fees. It is categorised as a Read tool in the Smokeball MCP Server, which means it retrieves data without modifying state.
Register the Smokeball MCP server in PolicyLayer and add a rule for list_fees: 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.
list_fees is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_fees 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 list_fees. 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.
list_fees 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 →