dbt MCP
by dbt Labs
Official listing: built and published by dbt Labs. More from dbt Labs
Exposes the dbt Semantic Layer, Discovery API, and dbt CLI over MCP so agents query governed metrics and inspect model lineage.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with dbt MCP connected:
- Semantic Layer Query
Use dbt MCP to query governed metrics and dimensions: ‹what you're looking for›
- Lineage Discovery
Use dbt MCP to read model metadata and lineage from the Discovery API: ‹what you need›
Connect it over MCP
{
"mcpServers": {
"dbt-mcp": {
"command": "uvx",
"args": [
"dbt-mcp"
]
}
}
}claude mcp add dbt-mcp -- uvx dbt-mcp
It runs on your computer, so web assistants such as Grok and ChatGPT can’t start it.
It may ask you to sign in to dbt Labs or for a key when you add it; the setup guide says which.
Setup guide: docs.getdbt.com/docs/dbt-ai/setup-local-mcp
Install the CLI
Install it as its own instructions say.
Setup guide: docs.getdbt.com/docs/dbt-ai/setup-local-mcp
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- MCPCLI
- Auth
- Bearer Token
- Skills
- 3
Skills
Semantic Layer Query
Queries governed metrics and dimensions through the dbt Semantic Layer so agent answers match approved definitions.
Lineage Discovery
Reads model metadata and lineage from the Discovery API to trace where a column or metric originates.
dbt Commands
Runs dbt CLI commands such as build, test, and compile from an agent session against a configured project.