AI agents use create_customer to create or update resources in Mcp Afip — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Afip environment.
This tool creates new customer records within the tax authority's electronic invoicing system. While reversible (customers can typically be modified or archived), it modifies the system state and could create fraudulent or duplicate customer entries if misused by an AI agent.
From the tool's definition Tool name 'create_customer' and description 'Create a customer' indicate creation of new data records in the AFIP (Argentine tax authority) system.
Documented attack patterns abuse exactly the kind of access create_customer 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_customer:
{
"version": "1",
"default": "deny",
"tools": {
"create_customer": {
"limits": [
{
"counter": "create_customer_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} create_customer stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a customer. It is categorised as a Write tool in the Mcp Afip MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for create_customer: 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_customer is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_customer 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_customer. 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_customer 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.