IDCloud: validate a Brazilian CNPJ with Receita Federal. Returns company status (ATIVA, BAIXADA, SUSPENSA, INAPTA), legal name, trade name, partners (QSA), address, and primary CNAE.
AI agents call validate_cnpj 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.
The tool queries an external registry (Receita Federal) to fetch and validate Brazilian company data. It performs a lookup operation with no side effects—no data is created, modified, deleted, or financial transactions are executed. This is a straightforward Read operation. The context of AP2 (payment protocol) is irrelevant to this specific tool's classification; the tool itself is purely informational.
From the tool's definition Tool validates and returns company information from Receita Federal—CNPJ status, legal name, trade name, partners, address, CNAE. Description explicitly indicates data retrieval ('Returns') with no modification or deletion operations mentioned.
Documented attack patterns abuse exactly the kind of access validate_cnpj 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_cnpj:
{
"version": "1",
"default": "deny",
"tools": {
"validate_cnpj": {}
}
} validate_cnpj 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.
IDCloud: validate a Brazilian CNPJ with Receita Federal. Returns company status (ATIVA, BAIXADA, SUSPENSA, INAPTA), legal name, trade name, partners (QSA), address, and primary CNAE. 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_cnpj: 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_cnpj 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_cnpj 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_cnpj. 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_cnpj 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.