Retrieve an invoice by code. Returns recipient details, status (DRAFT, OPEN, VIEWED, PAID, VOID), and the linked charge once payment begins.
AI agents call retrieve_invoice to retrieve information from Mcp Ap2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves invoice information (recipient details, status, charge data) but does not create, modify, delete, or execute any operations. It is a read-only query operation. While the tool exists within a financial payment protocol context (AP2), the tool itself performs no financial transactions, only data retrieval.
From the tool's definition Tool name is 'retrieve_invoice' and description states 'Retrieve an invoice' — a query operation that 'Returns recipient details, status...and the linked charge.' The verb 'retrieve' and 'returns' indicate data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access retrieve_invoice gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for retrieve_invoice:
{
"version": "1",
"default": "deny",
"tools": {
"retrieve_invoice": {}
}
}retrieve_invoice is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve an invoice by code. Returns recipient details, status (DRAFT, OPEN, VIEWED, PAID, VOID), and the linked charge once payment begins. It is categorised as a Read tool in the Mcp Ap2 MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for retrieve_invoice: 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 Mcp Ap2. Nothing to install.
retrieve_invoice 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 retrieve_invoice 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 retrieve_invoice. 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.
retrieve_invoice is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.