List reusable hosted checkouts, newest first. Cursor pagination via starting_after / ending_before.
AI agents call list_checkouts to retrieve information from Mcp Afip 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 existing checkout records in a paginated manner. It does not create, modify, delete, execute commands, or move money. While it accesses financial transaction data (checkouts in an AFIP context), the tool itself only reads/lists without triggering financial operations. The presence on a tax authority server does not change the fundamental read-only nature of the operation.
From the tool's definition Tool name and description: 'List reusable hosted checkouts, newest first. Cursor pagination via starting_after / ending_before.' The verb 'list' and the action of retrieving/querying checkout data with pagination parameters (starting_after/ending_before)…
Documented attack patterns abuse exactly the kind of access list_checkouts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Afip, and nothing reaches the server without passing your rules. This is the rule we recommend for list_checkouts:
{
"version": "1",
"default": "deny",
"tools": {
"list_checkouts": {}
}
} list_checkouts 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.
List reusable hosted checkouts, newest first. Cursor pagination via starting_after / ending_before. It is categorised as a Read tool in the Mcp Afip MCP Server, which means it retrieves data without modifying state.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for list_checkouts: 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 Afip. Nothing to install.
list_checkouts 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_checkouts 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_checkouts. 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_checkouts is provided by the Mcp Afip MCP server (codespar/mcp-dev-latam). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Afip, 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 Afip tools catalogued and risk-classified — across an index of 43,000+ MCP servers.