scherlok
Related Servers
Alternatives to scherlok
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceAgentic data quality MCP server — runs structured validation rules against warehouses (DuckDB, BigQuery, Athena, Databricks, Postgres), diagnoses failures with LLM root cause analysis, and proposes SQL remediations. Full audit trail of every AI decision.633 PyPI6Apache 2.0
- AlicenseNot gradedqualityCmaintenanceData observability for AI agents. Query alerts, monitor freshness, investigate schema drift, and trace lineage across your data warehouse via 53 MCP tools.1MIT
- AlicenseNot gradedqualityCmaintenanceAI-driven MCP server that audits, profiles, detects schema drift, and auto-generates documentation for dbt projects, enabling natural language interaction with your dbt project's health.105MIT
- AlicenseBqualityBmaintenanceLocal-first MCP server for data quality that finds suspicious data, explains findings with evidence, tracks drift, and supports human-approved, reversible repair workflows. Deterministic by default, with AI optional.25205 PyPI2Apache 2.0
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to audit dbt project health, profile warehouse data, detect schema drift, and auto-generate documentation through natural language. It combines coverage scoring, test suggestions, and non-destructive YAML updates in a single MCP server.-
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to audit project health, profile data, detect schema drift, and auto-generate documentation for dbt projects through natural language. It also provides coverage scoring, test suggestions, and safe schema.yml updates via MCP.-
TDQS
Scored across 8 tools
Most tools have clearly distinct roles: list_tables for discovery, investigate for baselines, watch for drift detection, and reconcile for source/target checks. The main overlap is among check, watch, and verify, which all perform anomaly detection and can return pass/fail gates, but the descriptions explicitly distinguish their persistence and read-only semantics.
Names are readable and consistently snake_case, but conventions are mixed: list_tables uses verb_noun, several tools are bare verbs (check, investigate, watch, verify, reconcile), and two are nouns (history, status). The set is understandable but not predictably patterned.
Eight tools is well-scoped for a data monitoring server, and each tool appears to earn its place across discovery, baseline creation, detection, gating, history, reconciliation, and status.
The core lifecycle is covered: discover tables, establish baselines, detect anomalies, run gates, inspect history, reconcile outputs, and check status. The notable gap is the lack of an accept-baseline tool even though multiple descriptions reference `scherlok accept` for resolving persistent CRITICAL anomalies, forcing a human/CLI workaround.