dbt MCP
Explore dbt models, lineage and test results from an AI agent.
Last verified: September 20, 2026
How to Install dbt MCP
$uvx dbt-mcpRequires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.
About dbt MCP
dbt's MCP server gives an agent access to the semantic layer, model definitions, lineage graph and test results in a dbt project. That turns questions like "what feeds this table and did its tests pass" into a single prompt instead of a manual trawl through the DAG. It is particularly effective during incident response, when tracing a bad number back through transformations is the slow part.
dbt MCP is a Database MCP server designed for developers, analysts, and data teams. It enables querying and managing databases from an AI assistant by exposing schema introspection and SQL execution as MCP tools. Key capabilities include schema introspection across tables and views, parameterised sql execution, read-only and read/write modes, and structured tool calls that work cleanly inside an LLM context. It integrates with Postgres, MySQL, SQLite, MongoDB, Redis, BigQuery, and Snowflake, and is best suited for developers, analysts, and data teams who need ad-hoc analytics without a bi tool.
Key Features
- dbt
- semantic-layer
- lineage
- analytics-engineering
- data-quality
Pricing
- Core MCP server
- Community support
- Works with any MCP client
- Everything in Free
- Higher usage limits
- Priority support
- Everything in Pro
- SLA & SSO
- Dedicated support
Tier details are indicative — visit the dbt MCP website for current pricing.
Pros & Cons
Pros
- Lets the assistant write and run real queries instead of guessing
- Read-only mode is safe to point at production-shaped data
- Skips most ORM and CSV-shuffling boilerplate
Cons
- Misconfigured permissions can expose sensitive data
- Long-running queries need explicit timeouts
- Schema drift requires reconnecting or refreshing context
Best For
- Ad-hoc analytics without a BI tool
- Drafting migrations and reviewing query plans
- Letting non-SQL teammates ask questions of a database
- Bootstrapping internal admin workflows
Screenshots
Screenshots coming soon —
Submit yours →Our Take on dbt MCP
Excellent for tracing lineage and test failures conversationally. Assumes a mature dbt project — thin value if your transformations live elsewhere.