Get the 5-tier agent capability stack — describes what the API can do.

List all supported connection types with their config schemas.

List all connections in the organization.

Get details of a specific connection by ID.

List schemas and tables of a source connection.

Args: connection_id: The connection to introspect. schema: Optional schema name to filter tables.

Preview the first N rows of a table from a source connection.

Args: connection_id: The connection to query. table: Table name to preview. schema: Optional schema name. limit: Max rows to return (default 100).

Execute a read-only SQL query against a source connection.

Args: connection_id: The connection to query. query: A single SELECT statement (no mutations allowed).

Compile a dbt transformation — resolves Jinja, ref(), source(). No execution.

Args: transformation_id: The transformation to compile.

Compile and execute a transformation, returning preview rows.

Args: transformation_id: The transformation to preview. limit: Max rows to return (default 100, max 1000).

List all uploads (extract + load jobs) in the organization.

List all pipelines (dbt transform orchestration) in the organization.

List all dbt transformations in the organization.

List pipeline/upload/transformation runs with optional filters.

Args: target_type: Filter by type — 'upload', 'pipeline', or 'transformation'. status: Filter by status — 'pending', 'running', 'success', 'failed', 'cancelled'. limit: Max results (default 50, max 200).

Get details of a specific run by ID.

Args: run_id: The run ID to look up.

Get the logs of a specific run.

Args: run_id: The run ID whose logs to fetch.

List all catalog entries (source tables and dbt models).

Get details of a specific catalog entry.

Args: entry_id: The catalog entry ID.

Create a new data connection.

Requires --allow-write.

Args: name: Human-readable name for the connection. connection_type: One of the supported types (e.g. 'postgres', 'mysql', 'stripe'). config: Connection-specific configuration (host, port, credentials, etc.).

Create a new upload (extract + load job).

Requires --allow-write.

Args: name: Upload name. source_connection_id: ID of the source connection. destination_connection_id: ID of the destination connection. dlt_config: Optional dlt extraction config (load_mode, table_name, etc.). description: Optional description.

Create a new pipeline (dbt transform orchestration).

Requires --allow-write.

Args: name: Pipeline name. destination_connection_id: ID of the destination connection. command: dbt command — 'run', 'build', 'test', 'seed', 'snapshot', 'compile'. description: Optional description.

Create a new dbt SQL transformation.

Requires --allow-write.

Args: name: Model name (letters, digits, underscores, hyphens; must start with letter or _). sql_body: dbt-compatible SQL (supports ref(), source(), Jinja). materialization: 'view', 'table', 'incremental', 'ephemeral', or 'snapshot'. description: Optional description. schema_name: Target schema (default 'staging').

Bulk-import connections, uploads, pipelines, and transformations in one call.

Requires --allow-write. Uses the JSON v2 import format. Validates everything first — if any errors, nothing is created.

Args: payload: JSON v2 import payload with version, connections, uploads, pipelines, transformations sections. See AI_IMPORT_GUIDE.md.

Trigger an upload run.

Requires --allow-write.

Args: upload_id: The upload to run. wait: If true, block until the run completes (up to 120s).

Trigger a pipeline run (dbt build/run/test).

Requires --allow-write.

Args: pipeline_id: The pipeline to run. wait: If true, block until the run completes (up to 120s).

Trigger a transformation run.

Requires --allow-write.

Args: transformation_id: The transformation to run. wait: If true, block until the run completes (up to 120s).