Skip to content
MCP server

GoldenCheck

Auto-discovers data validation rules from CSV and database data, with health scores

Pricing
Open source
Platforms
CLI, API, Linux
Runs
Locally or Remotely
Version
3.6.0
Listing updated
today

About GoldenCheck

GoldenCheck is an open-source MCP server for analytics and data. It can run locally on your machine or as a hosted remote server.

GoldenCheck flips the usual order of data validation: you scan a file first, it works out what healthy data looks like, and you then keep the rules worth enforcing. Findings carry a description, affected rows, sample values and a confidence level, and an interactive terminal interface lets you pin findings into a goldencheck.yml file that CI can enforce with exit codes.

The site describes 10 column profilers, 4 cross-column profilers, a learn-once statistical baseline with drift detection, domain packs for healthcare, finance and e-commerce, schema diffing, auto-fix, watch mode and scanning of Postgres, Snowflake and BigQuery. An optional LLM boost is quoted at about one cent per scan. It claims a DQBench score of 88.40 in zero-config mode against lower scores for Pandera, Soda Core and Great Expectations; that benchmark is the project's own.

The MCP server exposes nine tools to Claude Desktop and can run over stdio or a hosted HTTP endpoint. There are Python and TypeScript packages, and the original repository is archived after moving into the GoldenMatch monorepo.

Install

Run in a terminal

claude mcp add --transport http goldencheck https://goldencheck-mcp-production.up.railway.app/mcp/

Add to Settings → Connectors → Add custom connector

https://goldencheck-mcp-production.up.railway.app/mcp/
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "goldencheck": {
      "url": "https://goldencheck-mcp-production.up.railway.app/mcp/"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "goldencheck": {
      "serverUrl": "https://goldencheck-mcp-production.up.railway.app/mcp/"
    }
  }
}

Add to your client's MCP settings (most use this shape)

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

What it does

Rule discovery
Profiles data and proposes validation rules without hand-written configuration.
Interactive review
A terminal interface sorts findings by severity and lets you pin or dismiss them.
CI enforcement
Saved rules validate data with pass and fail exit codes.
Drift detection
Compares new data with a learned statistical baseline.
Database scanning
Scans Postgres, Snowflake and BigQuery directly.
Python and TypeScript
Available as pip and npm packages, with an edge-safe core.

Good for

  • Profile an unfamiliar CSV before loading it
  • Turn discovered issues into a rules file for a pipeline
  • Detect schema or distribution drift between data versions
  • Ask an assistant for a data health score

Pricing

Open source

Free open source; optional LLM boost about $0.01 per scan

Prices change. Check benseverndev-oss.github.io before you buy.

GoldenCheck FAQ

Do I have to write rules?

No. Rules are discovered from the data and you pin the ones to keep.

How much does the LLM boost cost?

The project quotes about $0.01 per scan and it needs an API key.

Where did the repository go?

The README says it moved into the benzsevern/goldenmatch monorepo and this repo is archived.

What transports does the MCP server use?

Stdio, and a hosted streamable HTTP endpoint.

Is GoldenCheck free?

Yes. GoldenCheck is open source, so you can use and self-host it for free.

How do I add GoldenCheck to Claude Code?

Run this command in your terminal: claude mcp add --transport http goldencheck https://goldencheck-mcp-production.up.railway.app/mcp/

What are the best alternatives to GoldenCheck?

The closest alternatives to GoldenCheck are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to GoldenCheck

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data