ANALYTICS ENGINEERING / dbt Labs
dbt MCP Server
Connects dbt project metadata and lineage with optional local CLI, Semantic Layer and Platform operations.
“This MCP (Model Context Protocol) server provides various tools to interact with dbt.”
01 / THE REASONING
Why this made the selection.
- Supports both project understanding and concrete build/test/job workflows.
- The configuration distinguishes discovery, local CLI, semantic and administrative tool groups.
02 / THE REVIEW RECORD
What we actually inspected.
Source review has boundaries.
A clear record is more useful than a “safe” badge.
Material inspected
- README.md (installation, capability and permission sections)
- pyproject.toml
- src/dbt_mcp/main.py
- src/dbt_mcp/config/settings.py
- LICENSE
- Official local MCP setup: launch command, toolset requirements and authentication table
- website/docs/docs/dbt-ai/setup-local-mcp.md in dbt-labs/docs.getdbt.com at 04abff2799aa5dc4c8a26088c6c3493ada96ea5c: CLI-only client block and default toolset switches
Our findings
- The README explicitly warns that CLI tools may modify data models, sources and warehouse objects.
- Settings provide allow/deny lists; an unset enable list means all configured tools rather than no tools.
- The current setup guide says missing required settings automatically disable the corresponding toolsets.
- The README lists CLI tools build, clone, compile, docs, list, parse, run, show and test, and Admin API tools including trigger_job_run, retry_job_run and cancel_job_run.
- The setup guide sets DISABLE_SQL and DISABLE_DBT_CODEGEN to true by default, so execute_sql, text_to_sql and the codegen tools stay off until enabled. The CLI, Semantic Layer, Discovery and Admin API toolsets default on when their settings exist.
- The README at this commit has no client configuration block. The example shown is the setup guide’s CLI-only block, which launches uvx dbt-mcp with DBT_PROJECT_DIR and DBT_PATH; it comes from the guide’s source file in dbt-labs/docs.getdbt.com, pinned above.
Not established by this review
- Server startup, authentication and tool execution were not tested.
The review applies to the material and revision named here. A newer upstream release can change its behavior.
03 / PUT IT TO WORK
Connect a server deliberately.
DOCUMENTED COMMAND
uvx dbt-mcp Copying does not execute this command. It may retrieve a newer version than the reviewed source.
- Use uvx dbt-mcp in the client configuration; set DBT_PROJECT_DIR and DBT_PATH for local CLI tools, or configure the documented Platform authentication.
- Provide the local project/runtime or the relevant dbt Platform credentials according to the selected mode.
Before you start
- A supported Python environment and dbt project/runtime or Platform account.
Documented configuration example
Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "/path/to/your/dbt/project",
"DBT_PATH": "/path/to/your/dbt/executable"
}
}
}
} 04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
- Official documentation ↗Checked
https://github.com/dbt-labs/dbt-mcp/blob/a9db3f0826f8cf2ed12fe787ef65d3204c57f251/README.md
Supports: summary, whySelected, bestFor, limitations, install, access, compatibility, transports, review
- Applicable source licence ↗Checked
https://github.com/dbt-labs/dbt-mcp/blob/a9db3f0826f8cf2ed12fe787ef65d3204c57f251/LICENSE
Supports: license
https://github.com/dbt-labs/dbt-mcp/blob/a9db3f0826f8cf2ed12fe787ef65d3204c57f251/pyproject.toml
Supports: language, review
https://github.com/dbt-labs/dbt-mcp/blob/a9db3f0826f8cf2ed12fe787ef65d3204c57f251/src/dbt_mcp/main.py
Supports: language, review
https://github.com/dbt-labs/dbt-mcp/blob/a9db3f0826f8cf2ed12fe787ef65d3204c57f251/src/dbt_mcp/config/settings.py
Supports: language, review
- dbt local MCP setup ↗Checked
https://docs.getdbt.com/docs/dbt-ai/setup-local-mcp
Supports: install, limitations, access, review
https://github.com/dbt-labs/docs.getdbt.com/blob/04abff2799aa5dc4c8a26088c6c3493ada96ea5c/website/docs/docs/dbt-ai/setup-local-mcp.md
Supports: configExample, review, Default toolset switches, execute_sql requires a personal access token