Guard Brasil

io.github.enioxtPublished by GitHub account enioxtv0.2.3Updated Oct 25, 2026

Detecta e mascara dado pessoal brasileiro (CPF, CNPJ, RG, e-mail) antes do texto ir a uma IA. LGPD.

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Brazilian LGPD privacy guard that inspects text for personal data such as CPF, CNPJ, RG and email, masks it, and flags unclassified residue before text goes to

What you can do
Inspect text for Brazilian personal data (CPF, CNPJ, RG, MASP, email, names) with an ethics validation step and get findings, a masked version of the text, unclassified residue and a recommendation. Run a quick PII scan that returns the masked text and any residue the rules cannot classify. Get a boolean safety verdict for public sharing, with a reason, that is never positive while unclassified residue remains.
When to use it
Use it when text containing Brazilian personal data may be sent to an AI model or published, and you want detection, masking and a share/no-share check aligned with LGPD.
Requirements
Runs as a remote endpoint or as a local npm package over stdio; no authentication, environment variables or headers are declared.
Before you install
Detection is rule-based and may leave residue it cannot classify, which is reported rather than cleared; masking is not a guarantee of anonymization, so review output before sharing or sending text to third parties.

Installation

In SourceWeft

  1. Open Guard Brasil in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.enioxt%2Fguard-brasil-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "guard-brasil": {
      "type": "http",
      "url": "https://guard.egos.ia.br/mcp"
    }
  }
}

README

This repository has no README.

Tools

3

guard_inspect

Guard Brasil: full inspection

Full LGPD PII inspection with ATRiAN ethics validation. Returns findings + textoMascarado + naoMedido (residue the rules cannot classify) + recommendation.

Parametersmasktextrequired

guard_scan_pii

Guard Brasil: quick PII scan

Quick PII scan (CPF, CNPJ, RG, MASP, EMAIL, names A–J). Returns textoMascarado + naoMedido.

Parameterstextrequired

guard_check_safe

Guard Brasil: safe-to-share check

Boolean safety check for public sharing. Returns safe/canShare/motivo/reason. Never safe:true with unclassified residue (motivo: nao-medido).

Parameterstextrequired

Version history

1
  1. v0.2.3LatestOct 14, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.