convez.ai
MCP ServerFinanceiroIntermediário
cognis-digital

ChargeGuard

cognis-digital/chargeguard

Monitora chargebacks e fraudes, gera evidências de representment automaticamente

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que monitora feeds de disputas e chargebacks, detecta violações de limites de taxa de fraude (VAMP/Visa) e gera pacotes de evidência para representação. Idealizado para merchants que precisam manter-se em conformidade com limites de chargeback do programa VAMP 2025.

Instalação

$npx convez-ai cognis-digital/chargeguard

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

  • Monitorar taxa de chargeback em tempo real contra limites VAMP/Visa
  • Automatizar detecção de padrões de fraude em transações
  • Gerar pacotes estruturados de evidência para disputas de pagamento

Veredito

Ferramenta essencial e prática para fintech e merchants que operam sob programas de conformidade de chargeback. Aborda um problema real e urgente (VAMP 2025) com CLI scriptável e integração nativa MCP para automação por agentes.

README

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

CHARGEGUARD

Monitors dispute/chargeback feeds, flags fraud-rate threshold breaches (VAMP/Visa), and drafts representment evidence packets.

PyPI CI License: COCL 1.0 Suite

Fintech & Payments Security — PCI, fraud, AML, and payment rails.

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

Contents

Why chargeguard?

Visa's VAMP program (2025) put hard chargeback-ratio ceilings on merchants; a CLI that watches your ratio and warns before you cross into the monitoring program is urgent and timely.

chargeguard 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

  • ✅ Load Records
  • ✅ Analyze Records
  • ✅ Analyze File
  • ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
  • ✅ Ports in Python, JavaScript, Go, and Rust (ports/)

Quick start

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

Example

$ chargeguard scan .
  [HIGH    ] CHA-001  example finding             (./src/app.py)
  [MEDIUM  ] CHA-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

chargeguard is interoperable with every popular way of using AI:

  • MCP server — chargeguard mcp (Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet)
  • OpenAI-compatible / JSON — pipe chargeguard 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 chargeguardStripe Radar
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 Stripe Radar / Chargebee disputes, 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 (chargeguard 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/chargeguard.git"    # pip (works today)
pipx install "git+https://github.com/cognis-digital/chargeguard.git"   # isolated CLI
uv tool install "git+https://github.com/cognis-digital/chargeguard.git" # uv
pip install cognis-chargeguard                                          # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/chargeguard:latest --help        # Docker
brew install cognis-digital/tap/chargeguard                             # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/chargeguard/main/install.sh | sh
LinuxmacOSWindowsDockerCloud
scripts/setup-linux.shscripts/setup-macos.shscripts/setup-windows.ps1docker run ghcr.io/cognis-digital/chargeguardDEPLOY.md (AWS/Azure/GCP/k8s)

Related Cognis tools

  • panhound — Scans code, logs, fixtures, and S3 buckets for leaked PANs (Luhn-validated card numbers) and CVVs before they hit prod.
  • fraudlens — Replays a stream of transactions against pluggable fraud rules and ML scorers, emitting precision/recall and alert volume from the terminal.
  • obscan — Conformance and security linter for Open Banking / FAPI APIs: validates OAuth flows, consent scopes, and PSD2 endpoints against the spec.
  • ledgerproof — Verifies double-entry ledger integrity and tamper-evidence by checking balance invariants and hash-chained journal entries.
  • iso20022 — Validates, lints, and diffs ISO 20022 / pacs / camt payment messages and translates legacy MT into MX with schema-aware errors.
  • tokenvault — Self-hostable PCI tokenization microservice and CLI that swaps PANs for format-preserving tokens and proves no raw card data persists.

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 chargeguard 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