MCP-Undetected-Chromedriver

Instructions

Args:
    key: The key to press - required, (e.g. 'Enter', 'ArrowDown', 'a')
    selector: Optional CSS selector to focus on before pressing the key - optional

Implementation Reference

• src/mcp_server_undetected_chromedriver/server.py:392-464 (handler)

  Implements the browser_press_key tool handler using Selenium's ActionChains to press keys, supporting special keys mapping and optional selector focus. Registered via @mcp.tool() decorator.

  @mcp.tool()
  async def browser_press_key(
          key: str,
          selector: str = None,
  ):
      """Press a key on the keyboard
  
      Args:
          key: The key to press - required, (e.g. 'Enter', 'ArrowDown', 'a')
          selector: Optional CSS selector to focus on before pressing the key - optional
      """
      assert key, "Key is required"
  
      async def press_key_handler(driver: uc.Chrome):
          # 如果提供了选择器，先找到元素并聚焦
          if selector:
              element = driver.find_element(By.CSS_SELECTOR, selector)
              element.click()  # 点击元素以确保聚焦
  
          # 处理特殊键
          special_keys = {
              'Enter': '\ue007',
              'Tab': '\ue004',
              'Escape': '\ue00c',
              'Space': '\ue00d',
              'Backspace': '\ue003',
              'Delete': '\ue017',
              'ArrowUp': '\ue013',
              'ArrowDown': '\ue015',
              'ArrowLeft': '\ue012',
              'ArrowRight': '\ue014',
              'PageUp': '\ue00e',
              'PageDown': '\ue00f',
              'Home': '\ue011',
              'End': '\ue010',
              'F1': '\ue031',
              'F2': '\ue032',
              'F3': '\ue033',
              'F4': '\ue034',
              'F5': '\ue035',
              'F6': '\ue036',
              'F7': '\ue037',
              'F8': '\ue038',
              'F9': '\ue039',
              'F10': '\ue03a',
              'F11': '\ue03b',
              'F12': '\ue03c',
          }
  
          # 映射按键
          key_to_send = special_keys.get(key, key)
  
          # 创建ActionChains对象
          actions = ActionChains(driver)
  
          # 发送按键
          if selector:
              element = driver.find_element(By.CSS_SELECTOR, selector)
              actions.send_keys_to_element(element, key_to_send)
          else:
              actions.send_keys(key_to_send)
  
          # 执行操作
          actions.perform()
  
          if selector:
              return await create_success_response(f"Pressed key '{key}' on element '{selector}'")
          else:
              return await create_success_response(f"Pressed key '{key}'")
  
      return await tool.safe_execute(
          ToolContext(webdriver=await ensure_browser()), press_key_handler
      )

• src/mcp_server_undetected_chromedriver/server.py:392-392 (registration)

  The @mcp.tool() decorator registers the browser_press_key function as an MCP tool.

  @mcp.tool()