# Guard Brasil

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

- name: io.github.enioxt/guard-brasil-mcp
- version: 0.2.3
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 81/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.enioxt%2Fguard-brasil-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.enioxt%2Fguard-brasil-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-5d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 81/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: guard_inspect (idempotentHint); guard_check_safe (idempotentHint); guard_scan_pii (idempotentHint)
- pass `tools.token_cost`: about 335 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 5 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know @egosbr/guard-brasil-mcp@0.2.3

- tools: 3, about 335 tokens to load them all
- tool set hash: 721e3a4567b9bd34a4f2edb7664cb708
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.enioxt/guard-brasil-mcp.svg)](https://protogrid.dev/servers/io.github.enioxt/guard-brasil-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm @egosbr/guard-brasil-mcp@0.2.3: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://guard.egos.ia.br/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- npm @egosbr/guard-brasil-mcp@0.2.3

## Tools (3)

- `guard_check_safe`: Boolean safety check for public sharing. Returns safe/canShare/motivo/reason. Never safe:true with unclassified residue (motivo: nao-medido).
- `guard_inspect`: Full LGPD PII inspection with ATRiAN ethics validation. Returns findings + textoMascarado + naoMedido (residue the rules cannot classify) + recommendation.
- `guard_scan_pii`: Quick PII scan (CPF, CNPJ, RG, MASP, EMAIL, names A–J). Returns textoMascarado + naoMedido.