convez.ai
MCP ServerAutomaçãoAvançado
simongonzalezdc

ComplyOS

simongonzalezdc/complyos

Motor de auditoria de conformidade nativo para IA em sistemas de L&D

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP Server para auditoria de conformidade e operações de aprendizagem empresarial. Fornece rastreamento de compliance com ledger de evidências, validação de regras de atribuição e integração nativa com LMS como Workday. Solução local-first baseada em SQLite, sem lock-in de SaaS.

Instalação

$npx convez-ai simongonzalezdc/complyos

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
1
Forks
0
Acompanhando
0
Saúde
57%
Último commit
há 1 semana
Versão
—
Issues abertas
1
Contribuidores
1

Casos de uso

  • Auditorias de conformidade em sistemas de aprendizagem empresarial
  • Validação de regras de atribuição antes de deployer para usuários em massa
  • Rastreamento de conclusão de cursos com evidência criptográfica
  • Sincronização e consulta de dados de LMS via Claude/Cursor

Veredito

Ferramenta sólida e bem arquitetada para times de L&D e compliance em enterprises. Resolve um problema real (auditoria de dados de aprendizagem) com abordagem engineer-first, ledger de evidências e suporte a múltiplos conectores LMS. Código maduro com CI/CD e documentação clara.

README

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

ComplyOS

CI Python 3.11+ Ruff License

L&D Compliance & Learning Operations MCP Server

An AI-native compliance auditing engine for enterprise learning management systems. Built by someone who spent 12 years in L&D ops and got tired of explaining to regulators why the CSV export didn't match the dashboard.


Why ComplyOS?

Enterprise compliance tracking is a disaster of CSV exports, stale dashboards, and "I thought they completed that" moments. ComplyOS treats compliance as a first-class engineering problem:

  • Evidence-backed audits — Every report includes a SHA256-hashed evidence ledger
  • Assignment rule validation — Test targeting rules before they hit 10,000 users
  • AI-native interface — Query status via Claude Code, Cursor, or any MCP client
  • Local-first — SQLite by default; no SaaS lock-in

Architecture

┌─────────────────┐     ┌──────────────────┐     ┌─────────────────┐
│   MCP Client    │────▶│  ComplyOS MCP    │────▶│ Compliance      │
│ (Claude/Cursor) │     │  Server (FastMCP)│     │ Auditor         │
└─────────────────┘     └──────────────────┘     └────────┬────────┘
                                                          │
                           ┌──────────────────────────────┼──────────────┐
                           │                              │              │
                    ┌──────▼──────┐            ┌──────────▼─────┐  ┌────▼─────┐
                    │   Mock      │            │   Workday      │  │  SAP/CSOD│
                    │ Connector   │            │   Connector    │  │ (planned)│
                    └─────────────┘            └────────────────┘  └──────────┘

Quick Start

Installation

# Clone the repo
git clone https://github.com/simongonzalezdc/complyos.git
cd complyos

# Install with uv (recommended)
uv sync --all-extras --dev

# Or with pip
pip install -e ".[dev]"

CLI Usage

# Run a compliance audit
complyos audit

# Filter by department
complyos audit --department Engineering

# Generate a structured report
complyos report --department Engineering --json

# Check a single user's status
complyos status u1

# Sync LMS data to local SQLite
complyos sync

# Validate an assignment rule before deploying
complyos validate-rule rule.json

# Preview who would be affected by a rule
complyos preview-rule rule.json

# Check connector health
complyos health

MCP Server

# Start the MCP server
complyos mcp

Then configure your MCP client (Claude Code, Cursor, etc.) to point to the server.


Connectors

PlatformStatusAuth
Workday Learning✅ SupportedBasic Auth (env vars)
Mock (seed data)✅ Built-inNone
SAP SuccessFactors🚧 PlannedOAuth 2.0
Cornerstone OnDemand🚧 PlannedAPI Key

Workday Configuration

Set environment variables:

export WORKDAY_BASE_URL="https://your-workday-instance.com"
export WORKDAY_USERNAME="your-user"
export WORKDAY_PASSWORD="your-pass"

Development

# Run tests
uv run pytest -q

# Run with coverage
uv run pytest --cov=complyos --cov-report=term-missing

# Lint
uv run ruff check complyos tests

# Type check
uv run mypy complyos --ignore-missing-imports

Domain Model

ComplianceGap(
    user=User(id="u1", department="Engineering", ...),
    missing_courses=[Course(code="SEC-101", mandatory=True)],
    severity=ComplianceGapSeverity.HIGH,  # critical | high | medium | low
    days_overdue=14,
    remediation_action=RemediationAction(...),
)

Every audit produces an EvidenceLedgerEntry with SHA256 hashes for regulator-ready audit trails.


Roadmap

  • Phase 1 — Core auditor, MCP server, CLI, Workday connector, tests
  • Phase 2 — SQLite persistence, assignment rules engine, sync command
  • Phase 3 — Remediation workflows, Web UI, Slack/Teams notifications

License

Apache-2.0

Ver o original no GitHub

Bom para

Relacionados