KYC: validate a CPF or CNPJ against Receita Federal. Returns registration status (REGULAR / SUSPENSA / CANCELADA / NULA / PENDENTE) and, when authorized, holder name and birth date.
AI agents call validate_document 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 is a Read operation—it queries external KYC/government data systems and retrieves document status and personal information. There are no side effects or modifications.
From the tool's definition The tool 'validate_document' performs KYC validation by querying government databases (Receita Federal) and returns registration status and personal information (holder name, birth date).
Documented attack patterns abuse exactly the kind of access validate_document 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 validate_document:
{
"version": "1",
"default": "deny",
"tools": {
"validate_document": {}
}
} validate_document 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.
KYC: validate a CPF or CNPJ against Receita Federal. Returns registration status (REGULAR / SUSPENSA / CANCELADA / NULA / PENDENTE) and, when authorized, holder name and birth date. 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 validate_document: 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.
validate_document 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 validate_document 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 validate_document. 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.
validate_document 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.