Guard Brasil
Detecta e mascara dado pessoal brasileiro (CPF, CNPJ, RG, e-mail) antes do texto ir a uma IA. LGPD.
Should I use this
Quality & Safety
Findings (1)
- LOWin guard_scan_pii
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"guard-brasil-mcp": {
"command": "npx",
"args": [
"@egosbr/guard-brasil-mcp"
]
}
}
}Runnable packages
0.2.3stdioRemote endpoints
https://guard.egos.ia.br/mcpstreamable-httpWhat it can do
Tool inventory
Tools (3)
🟢guard_inspect(text, mask)
Full LGPD PII inspection with ATRiAN ethics validation. Returns findings + textoMascarado + naoMedido (residue the rules cannot classify) + recommendation.
Input Schema
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to analyze for Brazilian PII"
},
"mask": {
"description": "Whether to mask detected PII (default: true)",
"type": "boolean"
}
},
"required": [
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢guard_scan_pii(text)
Quick PII scan (CPF, CNPJ, RG, MASP, EMAIL, names A–J). Returns textoMascarado + naoMedido.
Input Schema
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to scan"
}
},
"required": [
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢guard_check_safe(text)
Boolean safety check for public sharing. Returns safe/canShare/motivo/reason. Never safe:true with unclassified residue (motivo: nao-medido).
Input Schema
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to check"
}
},
"required": [
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence