GoldenPipe

io.github.benseverndev-ossPublished by GitHub account benseverndev-ossv1.5.0Updated Oct 24, 2026

One command to validate, transform, and deduplicate — chain GoldenCheck + Flow + Match.

VerifiedStreamable HTTPWeb executableDatabasesData & Analytics

Overview

AI-generated overview

GoldenPipe orchestrates a data-quality pipeline — profile, fix and deduplicate records — and exposes it as an MCP server, hosted or local.

What you can do
  • List the pipeline stages and explain their configurations
  • Validate the wiring of a pipeline setup
  • Run the full check-transform-match pipeline on a dataset and return quality findings, fixes, deduplicated clusters and the reasoning behind each decision
  • Skip transformation when no quality issues are found, or route to privacy-preserving matching when sensitive fields are detected
When to use it
Useful when an assistant needs to clean, standardize and deduplicate tabular records such as customer or contact lists, and to see why each pipeline decision was made, without wiring the three Golden Suite tools together by hand.
Requirements
Either the hosted remote endpoint, or a local install of the goldenpipe Python package with the mcp extra, started with the mcp-serve command (uvx/pip). No authentication, environment variables or headers are declared.
Before you install
The pipeline reads datasets and can write output files such as golden records; check where data is processed, since the hosted endpoint sends your data to a third-party server. The README notes the repository has moved and is archived, so the hosted endpoint may change.

Installation

In SourceWeft

  1. Open GoldenPipe in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.benseverndev-oss%2Fgoldenpipe/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "goldenpipe": {
      "type": "http",
      "url": "https://goldenpipe-mcp-production.up.railway.app/mcp/"
    }
  }
}

README

Moved. This repo has moved into the benzsevern/goldenmatch monorepo at packages/python/goldenpipe/. This repo is archived; new development happens in the monorepo.

GoldenPipe

Golden Suite orchestrator -- Check quality, fix issues, deduplicate records. One command. Built by Ben Severn.

[PyPI] [CI] [codecov] [Downloads] [Python 3.11+] [License: MIT] [Docs] [DQBench Pipeline] [Open In Colab]

What It Does

Raw Data  | GoldenCheck   -- profile & discover quality issues  | GoldenFlow    -- fix issues, standardize, reshape  | GoldenMatch   -- deduplicate, match, create golden records  vGolden 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 findingsprint(result.transform)     # What was fixedprint(result.match)         # Deduplicated clustersprint(result.reasoning)     # Why each decision was made

CLI

bash
goldenpipe run customers.csv                # Full pipelinegoldenpipe run customers.csv --verbose      # Show reasoninggoldenpipe run customers.csv --skip-flow    # Check + Match onlygoldenpipe run customers.csv --strategy pprl  # Force privacy modegoldenpipe run customers.csv -o golden.csv  # Save golden records

Remote MCP Server

GoldenPipe is available as a hosted MCP server on Smithery — 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

ToolPurposeInstall
GoldenCheckValidate & profile data qualitypip install goldencheck
GoldenFlowTransform & standardize datapip install goldenflow
GoldenMatchDeduplicate & match recordspip install goldenmatch
GoldenPipeOrchestrate the full pipelinepip install goldenpipe

Author

Ben Severn

License

MIT

Source: README.md at commit f9d2a6d

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.5.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts