dbt (data build tool) is an open-source command-line tool that enables data analysts and engineers to transform data in their warehouses using SQL. It helps organizations build reliable data pipelines and analytics workflows through version control, documentation, and testing.
Why this server?
Integrates with dbt pipelines to run data quality checks as part of transformation workflows.
Why this server?
Provides tools to interact with dbt, including executing dbt CLI commands (build, compile, run, test), accessing Semantic Layer for metric querying, and using Discovery API to explore models and their relationships in a dbt project.
Why this server?
Enables interaction with DBT (Data Build Tool) projects, allowing querying of project metadata, inspection of models, sources, and tests, viewing compiled SQL, running DBT commands, and accessing DBT documentation and lineage.
Why this server?
Provides tools for interacting with a dbt project, enabling AI agents to list models, tests, sources, exposures, macros, runs, check freshness, coverage, and explore the DAG using the project's manifest, run results, and catalog.
Why this server?
Allows AI agents to execute dbt CLI commands and interact with dbt projects. Supports operations like run, test, compile, list resources, debug, install dependencies, and load seed data.
Why this server?
Parses dbt manifests and projects as semantic sources via the ingest_source tool, enabling AI agents to work with dbt models, schemas, and business definitions for generating safe SQL queries.
Why this server?
Provides searchable documentation for dbt as part of the data engineering knowledge base.
Why this server?
Connects to the dbt Semantic Layer to provide access to business metrics, allowing users to browse available metrics, generate semantic queries, analyze data with filters and groupings, and visualize query results.
Why this server?
Provides access to dbt project metadata through manifest.json and catalog.json artifacts, enabling search of models, sources, and tests, inspection of node attributes, exploration of model dependencies, and tracing of column-level lineage within dbt projects.
