Read-only listing of invoice summaries from index.json with filters/pagination.
AI agents call list_invoices 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 retrieves and queries invoice data with no side effects. It performs filtering and pagination on existing data without creating, modifying, or deleting anything. The 'read-only' designation confirms it has no write or destructive capabilities.
From the tool's definition Tool name 'list_invoices' and description explicitly states 'Read-only listing of invoice summaries from index.json with filters/pagination.' No modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Read-only listing of invoice summaries from index.json with filters/pagination. 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 list_invoices: 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.
list_invoices 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_invoices 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_invoices. 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_invoices 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 →