AI agents call find_cpf_by_variations to retrieve information from Cpf Validador without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to generate or enumerate CPF variations to discover complete CPF numbers from partial input, which is a read operation that retrieves sensitive personal identification data. However, the empty description reduces confidence. The high severity reflects that CPF is Brazil's national ID number—unauthorized retrieval poses identity theft and fraud risk.
From the tool's definition Tool name 'find_cpf_by_variations' combined with sibling tool 'find_cpf_by_mask' and server description stating it 'discovers complete CPF from partial digits' indicates this retrieves/queries CPF data by generating or testing variations.
Documented attack patterns abuse exactly the kind of access find_cpf_by_variations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cpf Validador, and nothing reaches the server without passing your rules. This is the rule we recommend for find_cpf_by_variations:
{
"version": "1",
"default": "deny",
"tools": {
"find_cpf_by_variations": {}
}
}find_cpf_by_variations 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.
find_cpf_by_variations. It is categorised as a Read tool in the Cpf Validador MCP Server, which means it retrieves data without modifying state.
Register the Cpf Validador MCP server in PolicyLayer and add a rule for find_cpf_by_variations: 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 Cpf Validador. Nothing to install.
find_cpf_by_variations 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_cpf_by_variations 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_cpf_by_variations. 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_cpf_by_variations is provided by the Cpf Validador MCP server (opastorello/cpf-validador). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cpf Validador, 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.
6 Cpf Validador tools catalogued and risk-classified — across an index of 43,000+ MCP servers.