Source code and SQL models
AI Models & Assistants / Knowledge library
dbt (ChatGPT plugin)
dbt MCP Server helps users inspect dbt projects, query dbt Semantic Layer metrics, review lineage and model metadata, run dbt commands, manage dbt Platform jobs, generate dbt boilerplate, and search official dbt documentation through ChatGPT.
Why learn dbt (ChatGPT plugin)?
Brings dbt capabilities into ChatGPT so the assistant can work with that service's context.
The problem it solves
Reduces manual handoffs between ChatGPT and dbt.
Where it came from
dbt (ChatGPT plugin): dbt MCP Server helps users inspect dbt projects, query dbt Semantic Layer metrics, review lineage and model metadata, run dbt commands, manage dbt Platform jobs, generate dbt boilerplate, and search official dbt documentation through ChatGPT. Directory record checked 2026-10-12. Availability depends on region, plan, permissions and the publisher. Directory presence does not establish a quality ranking.
Build your understanding
Work through these exercises in order. Try the task before opening a reference.
- Explain what dbt (ChatGPT plugin) does.
- Identify a use case for dbt (ChatGPT plugin).
- Describe a limitation of dbt (ChatGPT plugin).
- Name a compatible tool for dbt (ChatGPT plugin).
- Compare dbt (ChatGPT plugin) against an alternative.
Documentation and sources
- Primary source / model card (chatgpt.com)
Catalog research notes
- See the AI Workbench for source dates, pricing evidence and configuration details.
Connect the ideas
Built on
Real World Example
Automated dbt Lineage and Metric Governance
Data engineering teams managing complex dbt projects with frequent schema changes.
The business problem
Manual documentation of dbt model dependencies and metric definitions is error-prone, leading to broken downstream dashboards and inconsistent business reporting.
How this topic solves it
Using the dbt MCP Server within ChatGPT, teams can programmatically inspect project lineage and query semantic layer metrics to ensure documentation matches the actual codebase without leaving the chat interface.
- Connect the dbt MCP Server to the project repository to index model metadata.
- Use the ChatGPT plugin interface to query the dbt Semantic Layer for current metric definitions.
- Generate boilerplate documentation for new models based on existing lineage patterns.
- Review model lineage graphs directly in the chat to identify potential breaking changes before deployment.
The flow shows how the dbt MCP Server bridges the gap between raw dbt code and human-readable documentation.
Interface for inspection and queries
User interaction layer
Generated boilerplate and lineage reports
- dbt Project → exposes metadata → dbt MCP Server
- dbt MCP Server → provides context → ChatGPT Interface
- ChatGPT Interface → generates output → Documentation
Expected business outcome
Improved consistency in data documentation and reduced time spent manually tracing dependencies during schema migrations.
Limitations and checks
The plugin relies on the current state of the dbt project; it cannot predict future schema changes that have not yet been committed to the repository, requiring users to verify the latest branch state manually.