Zero-dollar authorization / card validation (POST /zeroauth). Braspag routes a $0 (or minimum-amount) authorization through the acquirer to confirm the card is live and not blocked, without committing funds. Returns Valid=true/false plus ReturnCode/ReturnMessage. Useful before saving a card-on-fi...
AI agents invoke create_zero_auth to trigger actions in Mcp Afip. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation against a payment acquirer network (a $0 authorization request). It does not move money or commit financial obligations (no funds committed), but it does execute a real transaction attempt on the card network with external side effects.
From the tool's definition Zero-dollar authorization / card validation (POST /zeroauth). Braspag routes a $0 (or minimum-amount) authorization through the acquirer to confirm the card is live and not blocked, without committing funds.
Documented attack patterns abuse exactly the kind of access create_zero_auth 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 create_zero_auth:
{
"version": "1",
"default": "deny",
"tools": {
"create_zero_auth": {
"limits": [
{
"counter": "create_zero_auth_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} create_zero_auth stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Zero-dollar authorization / card validation (POST /zeroauth). Braspag routes a $0 (or minimum-amount) authorization through the acquirer to confirm the card is live and not blocked, without committing funds. Returns Valid=true/false plus ReturnCode/ReturnMessage. Useful before saving a card-on-file for future recurrence. It is categorised as a Execute tool in the Mcp Afip MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for create_zero_auth: 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.
create_zero_auth is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_zero_auth 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 create_zero_auth. 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.
create_zero_auth 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.