dbt MCP
Official dbt Labs MCP server covering SQL execution, Semantic Layer queries, Discovery API, dbt CLI, Admin API, dbt Codegen, dbt LSP, and Product Docs. 41 commits on main in the last 30 days, joint top cadence in this batch.
“Official dbt Labs MCP server covering SQL execution, Semantic Layer queries, Discovery API, dbt CLI, Admin API, dbt Codegen, dbt LSP, and Product Docs. 41 commits on main in the last 30 days, joint top cadence in this batch with Azure DevOps and Canvas LMS.”
INSTALL THIS SERVER
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_CLOUD_API_TOKEN": "<your-dbt-cloud-token>",
"DBT_CLOUD_ACCOUNT_ID": "<your-account-id>",
"DBT_PROJECT_DIR": "/path/to/dbt/project"
}
}
}
}
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_CLOUD_API_TOKEN": "<your-dbt-cloud-token>",
"DBT_CLOUD_ACCOUNT_ID": "<your-account-id>",
"DBT_PROJECT_DIR": "/path/to/dbt/project"
}
}
}
}
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_CLOUD_API_TOKEN": "<your-dbt-cloud-token>",
"DBT_CLOUD_ACCOUNT_ID": "<your-account-id>",
"DBT_PROJECT_DIR": "/path/to/dbt/project"
}
}
}
}
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_CLOUD_API_TOKEN": "<your-dbt-cloud-token>",
"DBT_CLOUD_ACCOUNT_ID": "<your-account-id>",
"DBT_PROJECT_DIR": "/path/to/dbt/project"
}
}
}
}
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_CLOUD_API_TOKEN": "<your-dbt-cloud-token>",
"DBT_CLOUD_ACCOUNT_ID": "<your-account-id>",
"DBT_PROJECT_DIR": "/path/to/dbt/project"
}
}
}
}
9 SELECTED TOOLS
OUR ASSESSMENT
dbt Labs ships an official MCP server with eight tool families. SQL executes against the dbt warehouse connection. Semantic Layer runs governed metric queries. Discovery API retrieves models, lineage, run results, exposures. dbt CLI tools run dbt locally (run, test, compile, build, seed, snapshot). Admin API manages dbt Cloud jobs. dbt Codegen scaffolds model, source, and test code. dbt LSP provides language-server tools for in-editor model authoring. Product Docs search covers official dbt documentation. Experimental MCP Bundle support flagged for early-access features.
- Official dbt Labs maintenance.
- 551 GitHub stars and Apache-2.0 licence.
- 41 commits on main in the last 30 days.
- Eight tool families cover the full dbt workflow: SQL, Semantic Layer, Discovery, CLI, Admin API, Codegen, LSP, Docs.
- Experimental MCP Bundle support flagged in the README for early-access features.
- Architecture documented in the README: clear separation between local dbt project tools and dbt Cloud Admin API.
- Setup complexity: requires a dbt project on disk plus optional dbt Cloud credentials for Admin API and Discovery surfaces.
- Semantic Layer and Discovery require dbt Cloud subscription; CLI and SQL work against any dbt project.
- The MCP Bundle feature is marked experimental; behaviour may evolve.
The MCP carries dbt Cloud API tokens (when configured) plus warehouse credentials from the dbt project profile. Scope dbt Cloud tokens to read-only when the agent does diagnostic work; the Admin API token grants full job management. The warehouse connection uses the credentials in the dbt project profile; for production agents, run the MCP under a dedicated read-only warehouse role.
Data teams using dbt for analytics engineering who want agents to execute SQL, query the Semantic Layer, inspect model lineage, and trigger dbt Cloud jobs from inside the editor; analytics engineers who want CLI run/test/build flows accessible from agent prompts; teams scaffolding new dbt models via Codegen.
TECHNICAL DETAILS
RECORDED ADOPTION METRICS
Saved directory snapshots. Record last checked MAY 3, 2026. The review date above does not refresh these figures.
// Recorded note551 stars on the dbt-labs/dbt-mcp repo. 41 commits on main in the last 30 days, joint top cadence in this batch.
// Recorded noteHighest-quality data MCP at time of review for analytics-engineering workflows.
SOURCES & RECORDED CHECKS
These are the directory listings and check details held in this record. Client compatibility, directory listings and installation testing are separate signals. Recorded client names describe the scope of a check; they do not establish a security assessment or a recurring test schedule.
The same server, 5 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.
| Source | Their rating | Their star count | Their downloads | Last synced |
|---|---|---|---|---|
| AutomationSwitch This page | 4.5editorial | 551 | — | MAY 3, 2026 |
| PulseMCP | — unrated | unavailable | unavailable | MAY 3, 2026 |
| MCP.so | — unrated | unavailable | unavailable | MAY 3, 2026 |
| Glama | — unrated | unavailable | unavailable | MAY 3, 2026 |
| Smithery | — unrated | unavailable | unavailable | MAY 3, 2026 |
| Official MCP Registry | — unrated | unavailable | unavailable | MAY 3, 2026 |
// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.
OTHER DATA / ANALYTICS MCP SERVERS
Firecrawl
Official Firecrawl MCP server for web search, page extraction and site discovery, with Markdown and structured content workflows.
Google Analytics MCP
Official Google MCP server for Google Analytics 4. Query reports, dimensions, metrics, custom audiences, and admin entities through MCP. 1,981 GitHub stars and 5 commits on main in the last 30 days. Apache-2.0.
Apify Actors MCP
Apify Actors as MCP tools: 6,000+ web scrapers, automation actors, and AI agents callable from Claude, Cursor, or any MCP client. Hosted streamable transport at https://mcp.apify.com plus stdio via npx. Dynamic actor discovery at runtime.
Tableau MCP
Tableau's official MCP server. Lets agents see and understand Tableau workbooks, datasources, and views over MCP. 259 GitHub stars and 12 commits on main in the last 30 days.
AntV Chart MCP
Visualization MCP and skills with 25+ chart types using AntV. Generate charts and analyse data from inside agents. 4,047 GitHub stars and 2 commits on main in the last 30 days.
Bright Data MCP
Web data extraction over the Bright Data network with two operating modes: Rapid Mode (free, basic search and scrape) and Pro Mode (60+ structured-dataset tools targeting Amazon, LinkedIn, Walmart, Instagram, and more).
DISCUSS YOUR
MCP REQUIREMENTS.
Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.