https://github.com/benzsevern/goldenpipe

Golden Suite orchestrator — chains validation, transformation, and entity resolution. 4 MCP tools on Smithery.
https://github.com/benzsevern/goldenpipe

a2a agent cli data-engineering data-orchestration data-pipeline data-quality etl fastapi golden-suite mcp mcp-server orchestration pipeline pluggable polars python remote-mcp tui yaml

Last synced: 2 months ago
JSON representation

Golden Suite orchestrator — chains validation, transformation, and entity resolution. 4 MCP tools on Smithery.

• Host: GitHub
• URL: https://github.com/benzsevern/goldenpipe
• Owner: benzsevern
• License: mit
• Created: 2026-03-25T21:06:40.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2026-04-03T14:51:02.000Z (2 months ago)
• Last Synced: 2026-04-03T18:35:26.628Z (2 months ago)
• Topics: a2a, agent, cli, data-engineering, data-orchestration, data-pipeline, data-quality, etl, fastapi, golden-suite, mcp, mcp-server, orchestration, pipeline, pluggable, polars, python, remote-mcp, tui, yaml
• Language: Python
• Homepage: https://smithery.ai/servers/benzsevern/goldenpipe
• Size: 128 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          

# GoldenPipe

**Golden Suite orchestrator** -- Check quality, fix issues, deduplicate records. One command.

[![PyPI](https://img.shields.io/pypi/v/goldenpipe?color=d4a017)](https://pypi.org/project/goldenpipe/)

[![CI](https://github.com/benzsevern/goldenpipe/actions/workflows/test.yml/badge.svg)](https://github.com/benzsevern/goldenpipe/actions/workflows/test.yml)

[![codecov](https://codecov.io/gh/benzsevern/goldenpipe/graph/badge.svg)](https://codecov.io/gh/benzsevern/goldenpipe)

[![Downloads](https://static.pepy.tech/badge/goldenpipe/month)](https://pepy.tech/project/goldenpipe)

[![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue)](https://python.org)

[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)

[![Docs](https://img.shields.io/badge/docs-benzsevern.github.io%2Fgoldenpipe-d4a017)](https://benzsevern.github.io/goldenpipe/)

[![DQBench Pipeline](https://img.shields.io/badge/DQBench%20Pipeline-88.07-gold)](https://github.com/benzsevern/dqbench)

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/benzsevern/goldenpipe/blob/main/scripts/goldenpipe_demo.ipynb)

## What It Does

```

Raw Data

  | GoldenCheck   -- profile & discover quality issues

  | GoldenFlow    -- fix issues, standardize, reshape

  | GoldenMatch   -- deduplicate, match, create golden records

  v

Golden Records

```

GoldenPipe orchestrates the full pipeline with adaptive logic:

- **Skips** transformation if no quality issues found

- **Routes** to privacy-preserving matching if sensitive fields detected

- **Reports** reasoning for every decision

## Install

```bash

pip install goldenpipe

```

## Quick Start

```python

import goldenpipe as gp

result = gp.run("customers.csv")

print(result.status)        # "success"

print(result.check)         # Quality findings

print(result.transform)     # What was fixed

print(result.match)         # Deduplicated clusters

print(result.reasoning)     # Why each decision was made

```

## CLI

```bash

goldenpipe run customers.csv                # Full pipeline

goldenpipe run customers.csv --verbose      # Show reasoning

goldenpipe run customers.csv --skip-flow    # Check + Match only

goldenpipe run customers.csv --strategy pprl  # Force privacy mode

goldenpipe run customers.csv -o golden.csv  # Save golden records

```

## Remote MCP Server

GoldenPipe is available as a hosted MCP server on [Smithery](https://smithery.ai/servers/benzsevern/goldenpipe) — connect from any MCP client without installing anything.

**Claude Desktop / Claude Code:**

```json

{

  "mcpServers": {

    "goldenpipe": {

      "url": "https://goldenpipe-mcp-production.up.railway.app/mcp/"

    }

  }

}

```

**Local server:**

```bash

pip install goldenpipe[mcp]

goldenpipe mcp-serve

```

4 tools available: list pipeline stages, validate wiring, run full check-transform-match pipeline, explain configs.

## Part of the Golden Suite

| Tool | Purpose | Install |

|------|---------|---------|

| [GoldenCheck](https://github.com/benzsevern/goldencheck) | Validate & profile data quality | `pip install goldencheck` |

| [GoldenFlow](https://github.com/benzsevern/goldenflow) | Transform & standardize data | `pip install goldenflow` |

| [GoldenMatch](https://github.com/benzsevern/goldenmatch) | Deduplicate & match records | `pip install goldenmatch` |

| [GoldenPipe](https://github.com/benzsevern/goldenpipe) | Orchestrate the full pipeline | `pip install goldenpipe` |

## License

MIT