convez.ai
MCP ServerFinanceiroIntermediário
cognis-digital

PayWatch

cognis-digital/paywatch

Detector de assinaturas recorrentes em extratos bancários, self-hostable e pronto para MCP

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que detecta automaticamente cobranças recorrentes e assinaturas a partir de CSVs bancários e Plaid. Processa extratos para identificar padrões de assinatura, normalizar merchants e gerar relatórios estruturados em JSON ou SARIF, com suporte nativo para agentes de IA.

Instalação

$npx convez-ai cognis-digital/paywatch

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

  • Auditoria de assinaturas ativas para reduzir custos operacionais
  • Automação de detecção de cobranças recorrentes em fluxos de conformidade
  • Integração em pipelines CI/CD para gating automático de achados financeiros

Veredito

Ferramenta especializada e bem-arquitetada para o nicho específico de detecção de assinaturas recorrentes. Excelente opção para equipes que precisam auditar custos SaaS sem depender de serviços terceirizados caros.

README

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

PAYWATCH

Recurring-charge and subscription detector from bank/Plaid CSV

PyPI CI License: COCL 1.0 Suite

Business Operations — run the company without a SaaS bill for every function.

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

Contents

Why paywatch?

consumer+SMB crossover, viral

paywatch 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

  • ✅ Normalize Merchant
  • ✅ Load Transactions
  • ✅ Detect Subscriptions
  • ✅ Summarize
  • ✅ Subscription To Dict
  • ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
  • ✅ Ports in Python, JavaScript, Go, and Rust (ports/)

Quick start

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

Example

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

paywatch is interoperable with every popular way of using AI:

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

Related Cognis tools

  • invoctl — CLI invoicing + payment-link generator with PDF and a local ledger
  • churnlens — Self-hosted SaaS metrics — MRR, churn, LTV from Stripe or CSV
  • leadforge — Lightweight MCP-native CRM pipeline with email sequences
  • quotecraft — Proposal / quote / SOW generator — YAML to branded PDF
  • boardroom — Investor-update and KPI one-pager generator from your metrics
  • seataudit — SaaS license, seat-usage and shadow-IT auditor

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 paywatch 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