ServiceNow MCP Server

Instructions

Implementation Reference

• src/servicenow_mcp/tools/workflow_tools.py:450-516 (handler)

  The core handler function for the 'create_workflow' MCP tool. It validates parameters, prepares the payload, and sends a POST request to the ServiceNow 'wf_workflow' table API to create a new workflow.

  def create_workflow(
      auth_manager: AuthManager,
      server_config: ServerConfig,
      params: Dict[str, Any],
  ) -> Dict[str, Any]:
      """
      Create a new workflow in ServiceNow.
      
      Args:
          auth_manager: Authentication manager
          server_config: Server configuration
          params: Parameters for creating a workflow
          
      Returns:
          Dict[str, Any]: Created workflow details
      """
      # Unwrap parameters if needed
      params = _unwrap_params(params, CreateWorkflowParams)
      
      # Get the correct auth_manager and server_config
      try:
          auth_manager, server_config = _get_auth_and_config(auth_manager, server_config)
      except ValueError as e:
          logger.error(f"Error getting auth and config: {e}")
          return {"error": str(e)}
      
      # Validate required parameters
      if not params.get("name"):
          return {"error": "Workflow name is required"}
      
      # Prepare data for the API request
      data = {
          "name": params["name"],
      }
      
      if params.get("description"):
          data["description"] = params["description"]
      
      if params.get("table"):
          data["table"] = params["table"]
      
      if params.get("active") is not None:
          data["active"] = str(params["active"]).lower()
      
      if params.get("attributes"):
          # Add any additional attributes
          data.update(params["attributes"])
      
      # Make the API request
      try:
          headers = auth_manager.get_headers()
          url = f"{server_config.instance_url}/api/now/table/wf_workflow"
          
          response = requests.post(url, headers=headers, json=data)
          response.raise_for_status()
          
          result = response.json()
          return {
              "workflow": result.get("result", {}),
              "message": "Workflow created successfully",
          }
      except requests.RequestException as e:
          logger.error(f"Error creating workflow: {e}")
          return {"error": str(e)}
      except Exception as e:
          logger.error(f"Unexpected error creating workflow: {e}")
          return {"error": str(e)}

• src/servicenow_mcp/tools/workflow_tools.py:55-62 (schema)

  Pydantic BaseModel defining the input schema (parameters) for the create_workflow tool, including required name and optional fields like description, table, active status, and attributes.

  class CreateWorkflowParams(BaseModel):
      """Parameters for creating a new workflow."""
      
      name: str = Field(..., description="Name of the workflow")
      description: Optional[str] = Field(None, description="Description of the workflow")
      table: Optional[str] = Field(None, description="Table the workflow applies to")
      active: Optional[bool] = Field(True, description="Whether the workflow is active")
      attributes: Optional[Dict[str, Any]] = Field(None, description="Additional attributes for the workflow")

• src/servicenow_mcp/utils/tool_utils.py:518-523 (registration)

  Registers the 'create_workflow' tool in the central tool definitions dictionary returned by get_tool_definitions(). Specifies the aliased handler function, input params model, return type hint, description, and serialization method for MCP server integration.

  "create_workflow": (
      create_workflow_tool,
      CreateWorkflowParams,
      str,  # Expects JSON string
      "Create a new workflow in ServiceNow",
      "json_dict",  # Tool returns Pydantic model

• src/servicenow_mcp/tools/workflow_tools.py:138-180 (helper)

  Helper function used by create_workflow (and other tools) to flexibly resolve AuthManager and ServerConfig instances, handling potential parameter order swaps.

  def _get_auth_and_config(
      auth_manager_or_config: Union[AuthManager, ServerConfig],
      server_config_or_auth: Union[ServerConfig, AuthManager],
  ) -> tuple[AuthManager, ServerConfig]:
      """
      Get the correct auth_manager and server_config objects.
      
      This function handles the case where the parameters might be swapped.
      
      Args:
          auth_manager_or_config: Either an AuthManager or a ServerConfig.
          server_config_or_auth: Either a ServerConfig or an AuthManager.
          
      Returns:
          tuple[AuthManager, ServerConfig]: The correct auth_manager and server_config.
          
      Raises:
          ValueError: If the parameters are not of the expected types.
      """
      # Check if the parameters are in the correct order
      if isinstance(auth_manager_or_config, AuthManager) and isinstance(server_config_or_auth, ServerConfig):
          return auth_manager_or_config, server_config_or_auth
      
      # Check if the parameters are swapped
      if isinstance(auth_manager_or_config, ServerConfig) and isinstance(server_config_or_auth, AuthManager):
          return server_config_or_auth, auth_manager_or_config
      
      # If we get here, at least one of the parameters is not of the expected type
      if hasattr(auth_manager_or_config, "get_headers"):
          auth_manager = auth_manager_or_config
      elif hasattr(server_config_or_auth, "get_headers"):
          auth_manager = server_config_or_auth
      else:
          raise ValueError("Cannot find get_headers method in either auth_manager or server_config")
      
      if hasattr(auth_manager_or_config, "instance_url"):
          server_config = auth_manager_or_config
      elif hasattr(server_config_or_auth, "instance_url"):
          server_config = server_config_or_auth
      else:
          raise ValueError("Cannot find instance_url attribute in either auth_manager or server_config")
      
      return auth_manager, server_config