AI Agent for Maintaining dbt Projects: Detect & Fix Schema Drift

AI Agent for Maintaining dbt Projects: Detect & Fix Schema Drift

This AI agent skill is designed to support developers and teams in maintaining dbt projects by detecting and addressing schema drift. It identifies discrepancies between the expected state and the current state of your data warehouse across multiple dimensions including schema, volume, grain, and semantics. By comparing a known-good baseline against the present state, it classifies the types of drift occurring and proposes rectifying edits to ensure data integrity and consistency.

What this skill does

• Detects schema drift such as changes in source columns and tables being added, dropped, retyped, or renamed.
• Identifies volume drift including situations where row counts have decreased, tables have emptied, or loads are incomplete.
• Highlights grain drift where key uniqueness is lost, row-per-entity cardinality changes, or join fanout increases.
• Monitors semantic drift where metric or dimension definitions no longer align, new categorical values emerge, or semantic references become unresolvable.
• Proposes manual, on-demand corrections to keep the dbt project synchronized with the evolving data landscape.

Who it is for

• Developers and data teams using dbt in their data management workflows.
• Teams operating within changing business environments or dynamic data warehouses.
• Users of AI coding agents such as Claude Code, Cursor, and Codex looking for dbt project maintenance support.

Use cases

• A developer notices a failing database test despite no code changes and suspects upstream changes.
• A data analyst queries the warehouse and sees unexpected changes in dashboard results.
• A database administrator needs to regularly ensure data model integrity amidst frequent warehouse modifications.

Technical details

• Integrates with AI coding agents like Claude Code, Cursor, and Codex to facilitate dbt project maintenance.
• Utilizes advanced detection algorithms to compare known-good baselines against real-time data observations.
• Operates manually and on-demand, with continuous drift detection and automated PRs offered as part of a commercial solution.

Source & Licence

This package is built on open-source work published by exmergo (exmergo/dex) and distributed under Apache-2.0. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted under the Apache License 2.0, which also includes an express patent grant. Attribution and any NOTICE file must be retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.