convez.ai
MCP ServerSegurançaIntermediário
cognis-digital

DPIAForge

cognis-digital/dpiaforge

Gerador de avaliações DPIA e conformidade EU AI Act em modo agent

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que gera avaliações de impacto DPIA (Data Protection Impact Assessment) e conformidade com a Lei de IA da UE. Ferramenta self-hostable que escaneia projetos, classifica riscos e produz relatórios auditáveis em múltiplos formatos, integrando-se nativamente com agentes Claude via MCP.

Instalação

$npx convez-ai cognis-digital/dpiaforge

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 4 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Avaliações de impacto em proteção de dados (DPIA) em pipelines CI/CD
  • Classificação de risco e conformidade com regulações de IA europeias
  • Auditorias de conformidade e compliance automatizadas em projetos

Veredito

Ferramenta especializada e bem-executada para compliance de dados e IA europeu. Destaca-se pela natureza MCP-first e capacidade de integração com agentes, preenchendo nicho crítico de automação regulatória em desenvolvimento.

README

A tradução para o português deste README ainda está na fila.

DPIAFORGE

DPIA and EU AI Act impact-assessment generator

PyPI CI License: COCL 1.0 Suite

Compliance & GRC — get audit-ready and stay there, self-hosted.

pip install cognis-dpiaforge
dpiaforge scan .            # → prioritized findings in seconds

Contents

Why dpiaforge?

AI governance wave

dpiaforge is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.

Features

  • ✅ Dpia Threshold
  • ✅ Classify Ai Act Tier
  • ✅ Risk Score
  • ✅ Assess
  • ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
  • ✅ Ports in Python, JavaScript, Go, and Rust (ports/)

Quick start

pip install cognis-dpiaforge
dpiaforge --version
dpiaforge scan .                       # scan current project
dpiaforge scan . --format json         # machine-readable
dpiaforge scan . --fail-on high        # CI gate (non-zero exit)

Example

$ dpiaforge scan .
  [HIGH    ] DPI-001  example finding             (./src/app.py)
  [MEDIUM  ] DPI-002  another signal              (./config.yaml)

  2 findings · risk score 5 · 38ms

Architecture

flowchart LR
  A[Input: file / dir / API] --> B[Collectors]
  B --> C[Rules / Analyzers]
  C --> D[Scorer]
  D --> E{Reporters}
  E --> F[Table]
  E --> G[JSON / SARIF]
  E --> H[MCP tool -. drives .-> AI agents]

Use it from any AI stack

dpiaforge is interoperable with every popular way of using AI:

  • MCP server — dpiaforge mcp (Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet)
  • OpenAI-compatible / JSON — pipe dpiaforge scan . --format json into any agent or LLM
  • LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
  • CI / scripts — exit codes + SARIF for non-AI pipelines

How it compares

Cognis dpiaforgeEU AI Act tooling
Self-hostable, no account✅varies
Single command, zero config✅⚠️
JSON + SARIF for CI✅varies
MCP-native (AI agents)✅❌
Polyglot ports (JS/Go/Rust)✅❌
Open license✅ COCLvaries

Built in the spirit of EU AI Act tooling, re-framed the Cognis way. Missing a credit? Open a PR.

Integrations

Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (dpiaforge mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.

Install — every way, every platform

pip install "git+https://github.com/cognis-digital/dpiaforge.git"    # pip (works today)
pipx install "git+https://github.com/cognis-digital/dpiaforge.git"   # isolated CLI
uv tool install "git+https://github.com/cognis-digital/dpiaforge.git" # uv
pip install cognis-dpiaforge                                          # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/dpiaforge:latest --help        # Docker
brew install cognis-digital/tap/dpiaforge                             # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/dpiaforge/main/install.sh | sh
LinuxmacOSWindowsDockerCloud
scripts/setup-linux.shscripts/setup-macos.shscripts/setup-windows.ps1docker run ghcr.io/cognis-digital/dpiaforgeDEPLOY.md (AWS/Azure/GCP/k8s)

Related Cognis tools

  • soc2box — SOC 2 evidence collector and control tracker, self-hosted
  • gdprkit — GDPR/CCPA DSAR, RoPA, and cookie-consent toolkit
  • policyforge — Auto-generate security policies from a short questionnaire
  • vendorvet — Third-party / vendor risk questionnaires with SBOM cross-ref
  • auditrail — Tamper-evident audit-log aggregator with hash-chained attestation
  • frameworkmap — Crosswalk controls across NIST, ISO 27001, SOC 2, CMMC, PCI

Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 hermes

Contributing

PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.

⭐ If dpiaforge saved you time, star it — it genuinely helps others find it.

License

Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.


Ver o original no GitHub

Bom para

Relacionados