Return the next invoice number using a yearly counter (default: YYYY-####).
AI agents call generate_invoice_number to retrieve information from Mad Invoice without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads/computes the next sequential invoice number from a counter. It retrieves information (a generated number) without creating, modifying, or deleting any invoice data. It is purely a read/query operation.
From the tool's definition Return the next invoice number using a yearly counter (default: YYYY-####)
Attacks that exploit this kind of access
Return the next invoice number using a yearly counter (default: YYYY-####). It is categorised as a Read tool in the Mad Invoice MCP Server, which means it retrieves data without modifying state.
Register the Mad Invoice MCP server in PolicyLayer and add a rule for generate_invoice_number: 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 Mad Invoice. Nothing to install.
generate_invoice_number 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 generate_invoice_number 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 generate_invoice_number. 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.
generate_invoice_number is provided by the Mad Invoice MCP server (mad-sol-dev/mad-invoice-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 →