Search for customers via the GraphQL search.customers query. Pass one of email / firstName / lastName / company to filter; returns matching customer nodes. Leave all blank to list the first page of customers.
AI agents call find_customer 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 customer data based on filter criteria (email, firstName, lastName, or company). It has no side effects—it only reads and returns information. The severity is low because customer list queries on a tax authority system have limited blast radius; exposing customer names and contact details is a data privacy concern but not immediately damaging compared to financial, destructive, or code-execution…
From the tool's definition Tool description states it "Search for customers" and "returns matching customer nodes." The operation is explicitly a search/query function with no modification or deletion capabilities.
Documented attack patterns abuse exactly the kind of access find_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 find_customer:
{
"version": "1",
"default": "deny",
"tools": {
"find_customer": {}
}
} find_customer 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.
Search for customers via the GraphQL search.customers query. Pass one of email / firstName / lastName / company to filter; returns matching customer nodes. Leave all blank to list the first page of customers. 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 find_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.
find_customer 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 find_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 find_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.
find_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.