Loading...
The dbt MCP server exposes dbt projects to AI agents, enabling read, write, and execution capabilities via a suite of tools for SQL, semantic layer, discovery, and admin tasks.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
The dbt MCP server exposes dbt projects to AI agents, enabling read, write, and execution capabilities via a suite of tools for SQL, semantic layer, discovery, and admin tasks.
The dbt MCP server offers powerful capabilities, but requires careful configuration and monitoring. Read-only tools are generally safe, while tools that modify data or execute code should be used with caution. Proper access controls and monitoring are essential to mitigate risks.
Performance depends on the complexity of the dbt project and the efficiency of the generated SQL. Consider optimizing dbt models and queries for better performance.
Cost depends on dbt Cloud usage, including the number of job runs and the resources consumed by SQL queries. Be mindful of API call limits and potential overages.
{
"mcpServers": {
"dbt-mcp": {
"command": "uvx",
"args": [
"--env-file",
"<path-to-.env-file>",
"dbt-mcp"
]
},
}
}MCPexecute_sqlExecutes SQL queries on dbt Platform infrastructure, leveraging Semantic Layer support.
Direct SQL execution can modify or expose sensitive data.
text_to_sqlGenerates SQL from natural language, using the dbt project context for assistance.
Poorly generated SQL could lead to inefficient queries or unintended data access.
get_model_detailsRetrieves detailed information about a specific dbt model, including compiled SQL and column definitions.
Read-only access to model metadata.
buildExecutes dbt models, tests, snapshots, and seeds in the order defined by the DAG.
Can modify data and project state.
trigger_job_runTriggers a dbt Cloud job run, with options to override settings like git branch and schema.
Can trigger unintended or malicious job executions.
generate_model_yamlGenerates model YAML files with column definitions, optionally inheriting descriptions from upstream models.
Modifies dbt project structure.
get_mcp_server_versionReturns the current version of the dbt MCP server.
Provides version information only.
API Key
cloud
The dbt MCP server offers powerful capabilities, but requires careful configuration and monitoring. Read-only tools are generally safe, while tools that modify data or execute code should be used with caution. Proper access controls and monitoring are essential to mitigate risks.
Autonomy levels depend on the specific tools used and the configured permissions. Exercise caution when granting full autonomy due to the potential for destructive actions.
Production Tip
Implement robust monitoring and alerting to detect and respond to errors or unexpected behavior.
It's a server that exposes dbt projects to AI agents, enabling interaction with dbt Core, Fusion, and Platform.
It's an experimental bundle that allows MCPB-aware clients to import the server without extra setup.
The dbt MCP server uses API keys for authentication.
SQL execution, Semantic Layer querying, dbt project Discovery, dbt CLI commands, Admin API access, dbt Codegen, and dbt LSP features.
Yes, some tools can modify dbt project configurations, execute dbt commands, and even execute arbitrary SQL.
Implement robust access controls, monitor API usage, and carefully review the permissions granted to AI agents.
Yes, the server provides access to dbt CLI commands like `run`, `test`, and `compile`.