ServiceNow MCP Server

Instructions

Implementation Reference

• src/servicenow_mcp/tools/workflow_tools.py:704-773 (handler)

  The main handler function that implements the logic for the 'add_workflow_activity' tool. It validates parameters, prepares the request data, and makes a POST API call to ServiceNow's wf_activity table to create the new activity.

  def add_workflow_activity(
      auth_manager: AuthManager,
      server_config: ServerConfig,
      params: Dict[str, Any],
  ) -> Dict[str, Any]:
      """
      Add a new activity to a workflow.
      
      Args:
          auth_manager: Authentication manager
          server_config: Server configuration
          params: Parameters for adding a workflow activity
          
      Returns:
          Dict[str, Any]: Added workflow activity details
      """
      # Unwrap parameters if needed
      params = _unwrap_params(params, AddWorkflowActivityParams)
      
      # 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
      workflow_version_id = params.get("workflow_version_id")
      if not workflow_version_id:
          return {"error": "Workflow version ID is required"}
      
      activity_name = params.get("name")
      if not activity_name:
          return {"error": "Activity name is required"}
      
      # Prepare data for the API request
      data = {
          "workflow_version": workflow_version_id,
          "name": activity_name,
      }
      
      if params.get("description"):
          data["description"] = params["description"]
      
      if params.get("activity_type"):
          data["activity_type"] = params["activity_type"]
      
      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_activity"
          
          response = requests.post(url, headers=headers, json=data)
          response.raise_for_status()
          
          result = response.json()
          return {
              "activity": result.get("result", {}),
              "message": "Workflow activity added successfully",
          }
      except requests.RequestException as e:
          logger.error(f"Error adding workflow activity: {e}")
          return {"error": str(e)}
      except Exception as e:
          logger.error(f"Unexpected error adding workflow activity: {e}")
          return {"error": str(e)}

• src/servicenow_mcp/tools/workflow_tools.py:88-96 (schema)

  Pydantic BaseModel defining the input schema/parameters for the 'add_workflow_activity' tool, including required fields like workflow_version_id, name, activity_type, and optional fields.

  class AddWorkflowActivityParams(BaseModel):
      """Parameters for adding an activity to a workflow."""
      
      workflow_version_id: str = Field(..., description="Workflow version ID")
      name: str = Field(..., description="Name of the activity")
      description: Optional[str] = Field(None, description="Description of the activity")
      activity_type: str = Field(..., description="Type of activity (e.g., 'approval', 'task', 'notification')")
      attributes: Optional[Dict[str, Any]] = Field(None, description="Additional attributes for the activity")

• src/servicenow_mcp/utils/tool_utils.py:546-552 (registration)

  The registration entry in the central tool_definitions dictionary that maps the tool name 'add_workflow_activity' to its handler function alias, params schema, return type hint, description, and serialization method.

  "add_workflow_activity": (
      add_workflow_activity_tool,
      AddWorkflowActivityParams,
      str,  # Expects JSON string
      "Add a new activity to a workflow in ServiceNow",
      "json_dict",  # Tool returns Pydantic model
  ),