DuckProbe
cognis-digital/duckprobe
Validação de dados em segundos, sem setup, via DuckDB e MCP
Ver no GitHubMCP server para verificações de qualidade de dados sem configuração prévia em arquivos ou data warehouses via DuckDB. Executa análises prioritárias, gera relatórios em múltiplos formatos (tabela, JSON, SARIF) e se integra nativamente com agentes de IA.
Instalação
npx convez-ai cognis-digital/duckprobe1 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
Casos de uso
- Validar qualidade de datasets antes de pipelines de IA
- Gate de qualidade em CI/CD para arquivos de dados
- Auditoria automatizada de data warehouses com agentes IA
Veredito

Ferramenta sólida e bem integrada ao ecossistema MCP para garantir qualidade de dados em tempo de desenvolvimento. Destaca-se pela simplicidade de uso (zero-setup) e suporte nativo a agentes Claude, ideal para pipelines data-driven.
README
A tradução para o português deste README ainda está na fila.
DUCKPROBE
Zero-setup data-quality checks on any file or warehouse via DuckDB
Data & Datasets — zero-setup quality, lineage, and governance.
pip install cognis-duckprobe
duckprobe scan . # → prioritized findings in seconds
Contents
- Why duckprobe? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
Why duckprobe?
DuckDB-era zero-setup DQ, hot
duckprobe 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 Table
- ✅ Parse Checks
- ✅ Run Checks
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
Quick start
pip install cognis-duckprobe
duckprobe --version
duckprobe scan . # scan current project
duckprobe scan . --format json # machine-readable
duckprobe scan . --fail-on high # CI gate (non-zero exit)
Example
$ duckprobe scan .
[HIGH ] DUC-001 example finding (./src/app.py)
[MEDIUM ] DUC-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
duckprobe is interoperable with every popular way of using AI:
- MCP server —
duckprobe mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
duckprobe scan . --format jsoninto 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 duckprobe | Soda Core + DuckDB | |
|---|---|---|
| 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 | ✅ COCL | varies |
Built in the spirit of Soda Core + DuckDB, 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 (duckprobe 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/duckprobe.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/duckprobe.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/duckprobe.git" # uv
pip install cognis-duckprobe # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/duckprobe:latest --help # Docker
brew install cognis-digital/tap/duckprobe # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/duckprobe/main/install.sh | sh
| Linux | macOS | Windows | Docker | Cloud |
|---|---|---|---|---|
scripts/setup-linux.sh | scripts/setup-macos.sh | scripts/setup-windows.ps1 | docker run ghcr.io/cognis-digital/duckprobe | DEPLOY.md (AWS/Azure/GCP/k8s) |
Related Cognis tools
schemadrift— Schema-change detector and data-contract testscsvlens— Fast CLI for profiling and cleaning huge CSV / Parquet filespiiscan— PII discovery across warehouses and lakes (data-side scanner)lineagemap— Column-level lineage extracted from SQL and dbtdatasetcard— Auto Dataset Cards / datasheets with Croissant + provenanceseedforge— Synthetic test-data generator with referential integrity
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
duckprobesaved 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.