Claude MarketplacesSubmit
benseverndev-oss avatar

GoldenCheck

benseverndev-oss/goldencheck

This server brings zero-config data validation into Claude. Instead of writing rules upfront, it scans CSVs or tabular data to auto-discover validation issues like nulls, outliers, format problems, and drift from learned baselines. You can scan a dataset, get findings with severity and confidence scores, pin the ones you care about, and export them to YAML for CI validation. It exposes operations to profile data, create baselines, detect drift, and optionally enhance findings with LLM-generated context. Available as both stdio and HTTP transports. Note that the repo has moved to a monorepo at benzsevern/goldenmatch, so check there for active development. Useful when you need quick data quality checks without setting up heavy validation frameworks first.

GitHub stars
2
tools
19
transport
STDIO, HTTP
last updated
Sep 25, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://goldencheck-mcp-production.up.railway.app/mcp/ --name goldencheck

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

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

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 19 tools

Verified live against the running server on Jun 10, 2026.

scanScan a data file (CSV, Parquet, Excel) for data quality issues. Returns findings with severity, confidence, affected rows, and sample values. No configuration needed — rules are discovered from the data.4 params

Scan a data file (CSV, Parquet, Excel) for data quality issues. Returns findings with severity, confidence, affected rows, and sample values. No configuration needed — rules are discovered from the data.

Parameters* required
file_path*string
Path to the data file (CSV, Parquet, Excel)
llm_boostboolean
Enable LLM enhancement (requires API key env var)default: false
llm_providerstring
LLM provider: 'anthropic' or 'openai'one of anthropic · openaidefault: anthropic
sample_sizeinteger
Max rows to sample (default 100000)default: 100000
validateValidate a data file against pinned rules in goldencheck.yml. Returns validation findings (existence, required, unique, enum, range checks).2 params

Validate a data file against pinned rules in goldencheck.yml. Returns validation findings (existence, required, unique, enum, range checks).

Parameters* required
config_pathstring
Path to goldencheck.yml (default: ./goldencheck.yml)default: goldencheck.yml
file_path*string
Path to the data file
profileProfile a data file and return column-level statistics: type, null%, unique%, min/max, top values, detected formats. Also returns a health score (A-F) based on finding severity.2 params

Profile a data file and return column-level statistics: type, null%, unique%, min/max, top values, detected formats. Also returns a health score (A-F) based on finding severity.

Parameters* required
file_path*string
Path to the data file
sample_sizeinteger
Max rows to sample (default 100000)default: 100000
health_scoreGet the health score (A-F, 0-100) for a data file. Quick summary of overall data quality.1 params

Get the health score (A-F, 0-100) for a data file. Quick summary of overall data quality.

Parameters* required
file_path*string
Path to the data file
list_checksList all available profiler checks and what they detect. No arguments needed.

List all available profiler checks and what they detect. No arguments needed.

No parameters. Call it with no arguments.

get_column_detailGet detailed profile and findings for a specific column.2 params

Get detailed profile and findings for a specific column.

Parameters* required
column*string
Column name to inspect
file_path*string
Path to the data file
list_domainsList all available domain packs (healthcare, finance, ecommerce, etc.). Domain packs provide specialized semantic type definitions for specific data domains.

List all available domain packs (healthcare, finance, ecommerce, etc.). Domain packs provide specialized semantic type definitions for specific data domains.

No parameters. Call it with no arguments.

get_domain_infoGet detailed info about a specific domain pack — lists all semantic types, their name hints, and suppression rules.1 params

Get detailed info about a specific domain pack — lists all semantic types, their name hints, and suppression rules.

Parameters* required
domain*string
Domain pack name (e.g., healthcare, finance, ecommerce)
install_domainDownload a community domain pack from the goldencheck-types repository and save it for use in future scans.2 params

Download a community domain pack from the goldencheck-types repository and save it for use in future scans.

Parameters* required
domain*string
Domain pack name to install
output_pathstring
Output path (default: goldencheck_domain.yaml)default: goldencheck_domain.yaml
analyze_dataAnalyze a data file to detect its domain, profile columns, and recommend a scanning strategy. Returns domain detection, column count, row count, strategy decisions, and alternative approaches.1 params

Analyze a data file to detect its domain, profile columns, and recommend a scanning strategy. Returns domain detection, column count, row count, strategy decisions, and alternative approaches.

Parameters* required
file_path*string
Path to the data file (CSV, Parquet, Excel)
auto_configureScan a data file, triage findings by confidence, and generate goldencheck.yml content from the pinned findings. Optionally accepts constraints to filter or adjust the generated config.2 params

Scan a data file, triage findings by confidence, and generate goldencheck.yml content from the pinned findings. Optionally accepts constraints to filter or adjust the generated config.

Parameters* required
constraintsobject
Optional constraints: {min_confidence, severity_filter, include_columns, exclude_columns}
file_path*string
Path to the data file
explain_findingExplain a single finding in natural language. Requires the finding as a JSON dict and the file_path to load a profile for context.2 params

Explain a single finding in natural language. Requires the finding as a JSON dict and the file_path to load a profile for context.

Parameters* required
file_path*string
Path to the data file (needed for profile context)
finding*object
Finding dict with keys: severity, column, check, message, affected_rows, confidence, sample_values
explain_columnGet a natural-language health narrative for a specific column. Scans the file, profiles the column, and explains all findings.2 params

Get a natural-language health narrative for a specific column. Scans the file, profiles the column, and explains all findings.

Parameters* required
column*string
Column name to explain
file_path*string
Path to the data file
review_queueList all pending review items for a given job. Returns items that need human decision (medium-confidence findings).1 params

List all pending review items for a given job. Returns items that need human decision (medium-confidence findings).

Parameters* required
job_name*string
Job name to filter review items
approve_rejectApprove (pin) or reject (dismiss) a review queue item. Decision must be 'pin' or 'dismiss'.3 params

Approve (pin) or reject (dismiss) a review queue item. Decision must be 'pin' or 'dismiss'.

Parameters* required
decision*string
Decision: 'pin' (approve) or 'dismiss' (reject)one of pin · dismiss
item_id*string
Review item ID to update
reasonstring
Optional reason for the decision
compare_domainsScan a file with every available domain pack (plus base/no-domain) and compare health scores. Recommends the best-fitting domain.1 params

Scan a file with every available domain pack (plus base/no-domain) and compare health scores. Recommends the best-fitting domain.

Parameters* required
file_path*string
Path to the data file
suggest_fixPreview fixes for a data file without applying them. Shows what would change (columns, fix types, rows affected, before/after samples).2 params

Preview fixes for a data file without applying them. Shows what would change (columns, fix types, rows affected, before/after samples).

Parameters* required
file_path*string
Path to the data file
modestring
Fix mode: 'safe' (default) or 'aggressive'one of safe · aggressivedefault: safe
pipeline_handoffGenerate a structured quality attestation JSON for a data file. Includes health score, findings summary, pinned rules, and attestation status (PASS, PASS_WITH_WARNINGS, REVIEW_REQUIRED, FAIL).2 params

Generate a structured quality attestation JSON for a data file. Includes health score, findings summary, pinned rules, and attestation status (PASS, PASS_WITH_WARNINGS, REVIEW_REQUIRED, FAIL).

Parameters* required
file_path*string
Path to the data file
job_name*string
Job name for the handoff record
review_statsGet review queue statistics for a job — counts of pending, pinned, and dismissed items.1 params

Get review queue statistics for a job — counts of pending, pinned, and dismissed items.

Parameters* required
job_name*string
Job name to get stats for

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

Moved. This repo has moved into the benzsevern/goldenmatch monorepo at packages/python/goldencheck (and packages/typescript/goldencheck)/. This repo is archived; new development happens in the monorepo.

GoldenCheck

Data validation that discovers rules from your data so you don't have to write them. Built by Ben Severn.

View the full README on GitHub

Details

Repository
github.com/benseverndev-oss/goldencheck
Website
benseverndev-oss.github.io/goldencheck
Category
Data & Analytics
Package
goldencheck
Transport
STDIO, HTTP
Registry
MCP registry, active
Tools verified
Jun 10, 2026

More from benseverndev-oss

Related Data & Analytics MCP servers

View all
1clk1st avatarMetricHub Quant - A股量化数据clk1st/mh-fin-mcpChina A-Share quantitative data: 5000+ stocks, 13 factors, daily market & limit-up analysis.2stars
2cmendezs avatarFattura Elettronica ITcmendezs/mcp-fattura-elettronica-itItalian e-invoicing: FatturaPA XML/SDI, XSD v1.2.3, Specs 1.9.1, 43 tools. Signing, SDI, archiving.2stars
3code-rabi avatarLittleSis API Servercode-rabi/littlesis-mcpProvide access to the LittleSis API to track corporate power and accountability. Enable querying and exploring relationships and entities related to corporate i2stars
4almured avatarAlmuredalmured/almured-mcpMarketplace where AI agents ask AI agents that have live or proprietary data.2stars
5cyanheads avatarCongressgov Mcp Servercyanheads/congressgov-mcp-serverAccess U.S. congressional data (bills, votes, members, committees) via MCP.2stars
6cyanheads avatarEpa Mcp Servercyanheads/epa-mcp-serverSearch EPA compliance, TRI, Superfund, drinking-water, EJScreen, and AirNow data.2stars