dbt MCP server: SQL execution, Semantic Layer metrics, Discovery API (lineage, models, sources, tests), dbt CLI (build, run, test), Admin API (jobs, runs), codegen, product docs search. For dbt Core, dbt Fusion, and dbt Platform.
dbt is a analytics and data insights platform that dbt mcp server: sql execution, semantic layer metrics, discovery api (lineage, models, sources, tests), dbt cli (build, run, test), admin api (jobs, runs), codegen, product docs search. for dbt core, dbt fusion, and dbt comprehensive platform.. The official dbt MCP server enables AI agents to seamlessly interact with dbt's platform, allowing developers to leverage AI capabilities within their existing workflows and automate complex tasks that would otherwise require manual intervention.
This official MCP server is maintained and verified by dbt, ensuring reliability, security, and up-to-date functionality. Unlike community-maintained servers, this official integration provides long-term support, comprehensive documentation, and direct vendor assistance. The server is hosted on getdbt.com, guaranteeing secure and reliable access to dbt's services.
Whether you're building AI-powered applications, automating workflows, or enhancing your development tools, the dbt MCP server provides a standardized way to connect AI agents with dbt's extensive platform capabilities. This integration enables natural language interactions with dbt, making it easier than ever to leverage dbt's features through AI assistants like Claude, ChatGPT, and Cursor.
Run via dbt-mcp or install dbt-mcp.mcpb bundle (stdio). Connects to dbt Core, Fusion, and Platform.Go to Settings → Cursor Settings
Click "Add new global MCP Server"
Paste the MCP configuration into mcp.json and restart
Or manually add to your mcp.json:
{
"mcpServers": {
"dbt": {
"url": "Run via dbt-mcp or install dbt-mcp.mcpb bundle (stdio). Connects to dbt Core, Fusion, and Platform."
}
}
}The official dbt MCP server enables AI agents to:
These capabilities make it easy for AI agents to work with dbt as part of a larger automation strategy, enabling seamless integration between AI assistants and your existing tools.
The dbt MCP server provides 31 tools for AI agents to interact with the platform. Use the search below to find specific tools.
| Tool Name | Description |
|---|---|
build | Execute models, tests, snapshots, seeds in DAG order (dbt CLI) |
compile | Generate executable SQL from models/tests; validate Jinja (dbt CLI) |
execute_sql | Execute SQL on dbt Platform infrastructure with Semantic Layer support |
generate_model_yaml | Generate model YAML with columns (dbt Codegen) |
generate_source | Generate source YAML by introspecting database schemas (dbt Codegen) |
generate_staging_model | Generate staging model SQL from a source table (dbt Codegen) |
get_all_models | Retrieve name and description of all models (Discovery) |
get_all_sources | Get all sources with freshness status (Discovery) |
get_dimensions | Get dimensions for specified metrics (Semantic Layer) |
get_entities | Get entities for specified metrics (Semantic Layer) |
get_exposures | Get all exposures (downstream dashboards, apps) (Discovery) |
get_job_run_details | Get run details including status, timing, steps, artifacts (Admin API) |
get_lineage | Get full lineage graph with type and depth filtering (Discovery) |
get_metrics_compiled_sql | Return compiled SQL for metrics without executing |
get_model_children | Get downstream dependents of a model (Discovery) |
get_model_details | Get model details including compiled SQL, columns, schema (Discovery) |
get_model_health | Get health signals: run status, test results, source freshness (Discovery) |
get_model_parents | Get upstream dependencies of a model (Discovery) |
get_product_doc_pages | Fetch full Markdown content of docs.getdbt.com pages by path or URL (Product Docs) |
get_source_details | Get source details including columns and freshness (Discovery) |
list_jobs | List jobs in dbt Platform account (Admin API) |
list_jobs_runs | List job runs with optional filters (Admin API) |
list_metrics | Retrieve all defined metrics (Semantic Layer) |
list_saved_queries | Retrieve all saved queries (Semantic Layer) |
parse | Parse and validate project files for syntax (dbt CLI) |
query_metrics | Execute metric queries with filtering and grouping (Semantic Layer) |
run | Execute models to materialize them (dbt CLI) |
search_product_docs | Search docs.getdbt.com for pages matching a query (Product Docs) |
test | Run tests to validate data and model integrity (dbt CLI) |
text_to_sql | Generate SQL from natural language using project context |
trigger_job_run | Trigger a job run; optional branch, schema overrides (Admin API) |
Last updated: March 13, 2026 at 12:00 PM
AI agents can use the dbt MCP server to automate repetitive tasks and manage workflows within dbt's platform.
The MCP server allows AI agents to query and retrieve data from dbt, enabling intelligent data analysis and insights.
Developers can integrate dbt capabilities directly into their AI coding assistants for seamless workflows.
Visit https://getdbt.com, create an account, and generate an API key from your dashboard. Most tools offer a free tier to get started, making it easy to begin using the dbt MCP server.
Yes, this MCP server is officially provided and maintained by dbt. The endpoint Run via dbt-mcp or install dbt-mcp.mcpb bundle (stdio). Connects to dbt Core, Fusion, and Platform. is hosted on their official domain getdbt.com, ensuring reliability and security.
The dbt MCP server requires appropriate API credentials and permissions based on the operations you want to perform. Check the documentation for specific permission requirements.
Yes, you can configure the same MCP server across Cursor, Claude Desktop, Cline, and other MCP-compatible clients simultaneously. Each client maintains its own configuration.
The MCP server itself is free to use, but you may need a dbt account and API access, which may have its own pricing tiers. Check https://getdbt.com for current pricing information.
The dbt MCP server enables AI agents to analyze data and generate insights. dbt MCP server: SQL execution, Semantic Layer metrics, Discovery API (lineage, models, sources, tests), dbt CLI (build, run, test), Admin API (jobs, runs), codegen, product docs search. For dbt Core, dbt Fusion, and dbt Platform. This allows you to interact with dbt's platform through natural language commands in your AI assistant.
Ensure your API key is correctly configured and your network allows outbound connections to getdbt.com. Verify that the MCP endpoint URL Run via dbt-mcp or install dbt-mcp.mcpb bundle (stdio). Connects to dbt Core, Fusion, and Platform. is accessible from your network.
Verify your API key is valid and has not expired. Generate a new key from https://getdbt.com if needed. Make sure you're using the correct authentication method as specified in the documentation.
Check dbt's status page for any ongoing incidents. Try restarting your MCP client and verify that the server endpoint is correct. If issues persist, consult the official documentation or support channels.
Explore other official MCP servers that work well with dbt:
The Model Context Protocol (MCP) is an open standard that enables AI models to securely connect to external APIs, tools, and data sources. This official MCP server from dbt provides standardized access to their services, allowing AI agents to interact with dbt's platform seamlessly.
To manage all your MCP servers in one place, use Apigene's MCP Gateway, which provides centralized management, security, and governance for all your MCP server connections.
Learn more about MCP in our complete guide or browse our FAQ for common questions.
Domain
getdbt.com
Website
https://getdbt.comMCP Endpoint
Run via dbt-mcp or install dbt-mcp.mcpb bundle (stdio). Connects to dbt Core, Fusion, and Platform.