Get XYZ values from Mediapipe hand model

Question

I want to draw a circle on my index finger. I need to process the coordinates of index finger. The landmark is 8, as stated on their website. I can read the x, and y of landmark 8 by

cap = cv2.VideoCapture(0)
with mp_hands.Hands(
    model_complexity=0,
    min_detection_confidence=0.5,
    min_tracking_confidence=0.5) as hands:
  while cap.isOpened():
    success, image = cap.read()
    if not success:
      print("Ignoring empty camera frame.")
      # If loading a video, use 'break' instead of 'continue'.
      continue

    # To improve performance, optionally mark the image as not writeable to
    # pass by reference.
    image.flags.writeable = False
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    results = hands.process(image)

    # Draw the hand annotations on the image.
    image.flags.writeable = True
    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    if results.multi_hand_landmarks:
        x = results.multi_hand_world_landmarks[0].landmark[8].x 
        y = results.multi_hand_world_landmarks[0].landmark[8].y

These x, and y are normalized values. So after googling, I found a solution that says to add image width and height to x, and y. But doing so doesn't solve my problem. I still see negative values and if I draw, it goes beyond the image scene. Here is the .py file and also the snipped below;

cap = cv2.VideoCapture(0)
with mp_hands.Hands(
    model_complexity=0,
    min_detection_confidence=0.5,
    min_tracking_confidence=0.5) as hands:
  while cap.isOpened():
    success, image = cap.read()
    if not success:
      print("Ignoring empty camera frame.")
      # If loading a video, use 'break' instead of 'continue'.
      continue

    # To improve performance, optionally mark the image as not writeable to
    # pass by reference.
    image.flags.writeable = False
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    results = hands.process(image)

    # Draw the hand annotations on the image.
    image.flags.writeable = True
    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    if results.multi_hand_landmarks:
        x = results.multi_hand_world_landmarks[0].landmark[8].x 
        y = results.multi_hand_world_landmarks[0].landmark[8].y
        z = results.multi_hand_world_landmarks[0].landmark[8].z
        
        shape = image.shape 
        relative_x = int(x * shape[1])
        relative_y = int(y * shape[0])
        # Center coordinates
#         center_coordinates = (results.multi_hand_world_landmarks[0].landmark[4].x, results.multi_hand_world_landmarks[0].landmark[4].y)
        print(relative_x, relative_y, x, y, z)
        # Radius of circle
        radius = 20

        # Blue color in BGR
        color = (255, 0, 0)

        # Line thickness of 2 px
        thickness = 2

        # Using cv2.circle() method
        # Draw a circle with blue line borders of thickness of 2 px
        image = cv2.circle(image, (relative_x, relative_y), radius, color, thickness)