AI agents call get_invoice_download_url 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 a download URL for an existing invoice document. It performs a read-only operation that queries and returns data without side effects. No financial transaction is initiated, no data is modified or deleted, and no external operations are executed. The action is purely informational retrieval suitable for the Read category.
From the tool's definition Tool name 'get_invoice_download_url' and description 'Get a download URL for an invoice PDF' indicate retrieval of a resource URL with no modification, creation, or deletion of data.
Attacks that exploit this kind of access
Get a download URL for an invoice PDF. 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 get_invoice_download_url: 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.
get_invoice_download_url 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 get_invoice_download_url 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 get_invoice_download_url. 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.
get_invoice_download_url 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 →