Busca com MULTIPLOS FILTROS combinados. QUANDO USAR: - Precisa de filtros que outras ferramentas nao oferecem - Query complexa combinando varios criterios FILTROS DISPONIVEIS: - cnae, uf, municipio, porte - capital_min/capital_max - situacao, limite
AI agents call buscar_avancado to retrieve information from MCP CNPJ Intelligence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search and query tool that retrieves company data from a Federal Revenue database based on various filter criteria. It has no side effects—it only reads and returns data matching the specified filters. It does not create, modify, delete, or execute any operations. The blast radius of misuse is limited to potential information disclosure about public Brazilian company records, which represents low risk.
From the tool's definition Tool name 'buscar_avancado' (advanced search) and description indicate querying/filtering across 27 million Brazilian company records with multiple combined filters (cnae, uf, municipio, porte, capital ranges, situacao, limite).
Attacks that exploit this kind of access
Busca com MULTIPLOS FILTROS combinados. QUANDO USAR: - Precisa de filtros que outras ferramentas nao oferecem - Query complexa combinando varios criterios FILTROS DISPONIVEIS: - cnae, uf, municipio, porte - capital_min/capital_max - situacao, limite. It is categorised as a Read tool in the MCP CNPJ Intelligence MCP Server, which means it retrieves data without modifying state.
Register the MCP CNPJ Intelligence MCP server in PolicyLayer and add a rule for buscar_avancado: 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 CNPJ Intelligence. Nothing to install.
buscar_avancado 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 buscar_avancado 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 buscar_avancado. 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.
buscar_avancado is provided by the MCP CNPJ Intelligence MCP server (raphaelmarra/mcp-cnpj-intelligence). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →