// MCP TOOL REFERENCE

GOLDENCHECK TOOLS

31 tools from the GoldenCheck MCP Server, categorised by risk level.

// ALL 31 GOLDENCHECK TOOLS

READ 27 tools

Read analyze_data Analyze a data file to detect its domain, profile columns, and recommend a scanning strategy. Returns domai... Read cardinality Identifies enum candidates Read compare_domains Scan a file with every available domain pack (plus base/no-domain) and compare health scores. Recommends th... Read cross_column Cross-column: age vs DOB mismatches Read cross_column_validation Cross-column: value > max violations Read drift_detection Detects distribution shifts Read encoding_detection Detects encoding issues and control chars Read explain_column Get a natural-language health narrative for a specific column. Scans the file, profiles the column, and exp... Read explain_finding Explain a single finding in natural language. Requires the finding as a JSON dict and the file_path to load... Read format_detection Validates email, phone, URL formats Read get_column_detail Get detailed profile and findings for a specific column. Read get_domain_info Get info about a domain pack \u2014 types, hints, suppression rules. Read health_score Get health score (A-F, 0-100) for a data file. Read list_checks List all available profiler checks and what they detect. Read list_domains List available domain packs (healthcare, finance, ecommerce). Read null_correlation Cross-column: correlated nulls Read nullability Identifies required vs optional columns Read pattern_consistency Detects mixed formats within columns Read pipeline_handoff Generate a structured quality attestation for a data file: health score, findings summary, pinned rules, an... Read profile Profile a data file \u2014 column types, null%, unique%, min/max, health score. Read range_distribution Finds outliers in numeric columns Read review_queue List all pending review items for a given job (medium-confidence findings needing a decision). Read review_stats Get review queue statistics for a job \u2014 counts of pending, pinned, and dismissed items. Read scan Scan a data file (CSV, Parquet) for data quality issues. Returns findings with severity, confidence, affect... Read sequence_detection Finds gaps in sequential columns Read suggest_fix Preview fixes for a data file without applying them. Shows what would change (columns, fix types, rows affe... Read uniqueness Finds primary key candidates and duplicates

WRITE 3 tools

Write approve_reject Approve (pin) or reject (dismiss) a review queue item. Decision must be Write auto_configure Scan a data file, triage findings by confidence, and generate goldencheck.yml content from the pinned findi... Write type_inference Detects columns stored as wrong types

EXECUTE 1 tools

Execute temporal_order Cross-column: start > end violations

// RUNNING THIS SERVER

The managed route: connect GoldenCheck through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y goldencheck

// FAQ

How many tools does the GoldenCheck MCP server have? +

The GoldenCheck MCP server exposes 31 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on GoldenCheck tools? +

Route the GoldenCheck server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do GoldenCheck tools fall into? +

GoldenCheck tools are categorised as Read (27), Write (3), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.