DBT Core MCP Server

Instructions

Implementation Reference

• src/dbt_core_mcp/server.py:1026-1106 (handler)

  Main handler function that implements the build_models tool logic: prepares dbt build command with selectors (state:modified, manual select/exclude), executes via runner, handles progress reporting, parses results from run_results.json, saves state manifest for future modified runs.

      self,
      ctx: Context | None,
      select: str | None = None,
      exclude: str | None = None,
      select_state_modified: bool = False,
      select_state_modified_plus_downstream: bool = False,
      full_refresh: bool = False,
      fail_fast: bool = False,
  ) -> dict[str, Any]:
      """Implementation of build_models tool."""
      # Prepare state-based selection (validates and returns selector)
      selector = await self._prepare_state_based_selection(select_state_modified, select_state_modified_plus_downstream, select)
  
      # Early return if state-based requested but no state exists
      if select_state_modified and not selector:
          return {
              "status": "success",
              "message": "No previous state found - cannot determine modifications",
              "results": [],
              "elapsed_time": 0,
          }
  
      # Build command args
      args = ["build"]
  
      # Add selector if we have one (state-based or manual)
      if selector:
          args.extend(["-s", selector, "--state", "target/state_last_run"])
      elif select:
          args.extend(["-s", select])
  
      if exclude:
          args.extend(["--exclude", exclude])
  
      if full_refresh:
          args.append("--full-refresh")
  
      if fail_fast:
          args.append("--fail-fast")
  
      # Execute with progress reporting
      logger.info(f"Running DBT build with args: {args}")
  
      # Define progress callback if context available
      async def progress_callback(current: int, total: int, message: str) -> None:
          if ctx:
              await ctx.report_progress(progress=current, total=total, message=message)
  
      result = await self.runner.invoke(args, progress_callback=progress_callback if ctx else None)  # type: ignore
  
      if not result.success:
          error_msg = str(result.exception) if result.exception else "Build failed"
          response = {
              "status": "error",
              "message": error_msg,
              "command": " ".join(args),
          }
          # Include dbt output for debugging
          if result.stdout:
              response["dbt_output"] = result.stdout
          if result.stderr:
              response["stderr"] = result.stderr
          return response
  
      # Save state on success for next modified run
      if result.success and self.project_dir:
          state_dir = self.project_dir / "target" / "state_last_run"
          state_dir.mkdir(parents=True, exist_ok=True)
          manifest_path = self.runner.get_manifest_path()  # type: ignore
          shutil.copy(manifest_path, state_dir / "manifest.json")
  
      # Parse run_results.json for details
      run_results = self._parse_run_results()
  
      return {
          "status": "success",
          "command": " ".join(args),
          "results": run_results.get("results", []),
          "elapsed_time": run_results.get("elapsed_time"),
      }

• src/dbt_core_mcp/server.py:1604-1637 (registration)

  MCP tool registration for 'build_models' using @app.tool() decorator. Defines input parameters and docstring schema. Calls the internal toolImpl_build_models handler after initialization.

  async def build_models(
      ctx: Context,
      select: str | None = None,
      exclude: str | None = None,
      select_state_modified: bool = False,
      select_state_modified_plus_downstream: bool = False,
      full_refresh: bool = False,
      fail_fast: bool = False,
  ) -> dict[str, Any]:
      """Run DBT build (run + test in DAG order).
  
      State-based selection modes (uses dbt state:modified selector):
      - select_state_modified: Build only models modified since last successful run (state:modified)
      - select_state_modified_plus_downstream: Build modified + downstream dependencies (state:modified+)
        Note: Requires select_state_modified=True
  
      Manual selection (alternative to state-based):
      - select: dbt selector syntax (e.g., "customers", "tag:mart", "stg_*")
      - exclude: Exclude specific models
  
      Args:
          select: Manual selector
          exclude: Exclude selector
          select_state_modified: Use state:modified selector (changed models only)
          select_state_modified_plus_downstream: Extend to state:modified+ (changed + downstream)
          full_refresh: Force full refresh of incremental models
          fail_fast: Stop execution on first failure
  
      Returns:
          Build results with status, models run/tested, and timing info
      """
      await self._ensure_initialized_with_context(ctx)
      return await self.toolImpl_build_models(ctx, select, exclude, select_state_modified, select_state_modified_plus_downstream, full_refresh, fail_fast)

• src/dbt_core_mcp/server.py:480-521 (helper)

  Helper function to validate and prepare dbt state-based selectors (state:modified or state:modified+) for build_models and similar tools. Handles conflicts and checks for existing state.

      self,
      select_state_modified: bool,
      select_state_modified_plus_downstream: bool,
      select: str | None,
  ) -> str | None:
      """Validate and prepare state-based selection.
  
      Args:
          select_state_modified: Use state:modified selector
          select_state_modified_plus_downstream: Extend to state:modified+
          select: Manual selector (conflicts with state-based)
  
      Returns:
          The dbt selector string to use ("state:modified" or "state:modified+"), or None if:
          - Not using state-based selection
          - No previous state exists (cannot determine modifications)
  
      Raises:
          ValueError: If validation fails
      """
      # Validate: hierarchical requirement
      if select_state_modified_plus_downstream and not select_state_modified:
          raise ValueError("select_state_modified_plus_downstream requires select_state_modified=True")
  
      # Validate: can't use both state-based and manual selection
      if select_state_modified and select:
          raise ValueError("Cannot use both select_state_modified* flags and select parameter")
  
      # If not using state-based selection, return None
      if not select_state_modified:
          return None
  
      # Check if state exists
      state_dir = self.project_dir / "target" / "state_last_run"  # type: ignore
      if not state_dir.exists():
          # No state - cannot determine modifications
          return None
  
      # Return selector (state exists)
      return "state:modified+" if select_state_modified_plus_downstream else "state:modified"
  
  async def toolImpl_get_resource_info(

• src/dbt_core_mcp/server.py:305-341 (helper)

  Helper to parse dbt's run_results.json after build/run/test, simplifying results for tool output.

  """Parse target/run_results.json after dbt run/test/build.
  
  Returns:
      Dictionary with results array and metadata
  """
  if not self.project_dir:
      return {"results": [], "elapsed_time": 0}
  
  run_results_path = self.project_dir / "target" / "run_results.json"
  if not run_results_path.exists():
      return {"results": [], "elapsed_time": 0}
  
  try:
      with open(run_results_path) as f:
          data = json.load(f)
  
      # Simplify results for output
      simplified_results = []
      for result in data.get("results", []):
          simplified_results.append(
              {
                  "unique_id": result.get("unique_id"),
                  "status": result.get("status"),
                  "message": result.get("message"),
                  "execution_time": result.get("execution_time"),
                  "failures": result.get("failures"),
              }
          )
  
      return {
          "results": simplified_results,
          "elapsed_time": data.get("elapsed_time", 0),
      }
  except Exception as e:
      logger.warning(f"Failed to parse run_results.json: {e}")
      return {"results": [], "elapsed_time": 0}