Playwright Server MCP

Instructions

Implementation Reference

• src/playwright_server/server.py:281-322 (handler)

  The GetTextContentToolHandler class that executes the tool logic: checks for active session, evaluates JavaScript to extract unique text from visible elements with <=3 children and their values, returns the list of texts.

  class GetTextContentToolHandler(ToolHandler):
      async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
          if not self._sessions:
              return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
          session_id = list(self._sessions.keys())[-1]
          page = self._sessions[session_id]["page"]
          # text_contents = await page.locator('body').all_inner_texts()
  
  
          async def get_unique_texts_js(page):
              unique_texts = await page.evaluate('''() => {
              var elements = Array.from(document.querySelectorAll('*')); // 先选择所有元素，再进行过滤
              var uniqueTexts = new Set();
  
              for (var element of elements) {
                  if (element.offsetWidth > 0 || element.offsetHeight > 0) { // 判断是否可见
                      var childrenCount = element.querySelectorAll('*').length;
                      if (childrenCount <= 3) {
                          var innerText = element.innerText ? element.innerText.trim() : '';
                          if (innerText && innerText.length <= 1000) {
                              uniqueTexts.add(innerText);
                          }
                          var value = element.getAttribute('value');
                          if (value) {
                              uniqueTexts.add(value);
                          }
                      }
                  }
              }
              //console.log( Array.from(uniqueTexts));
              return Array.from(uniqueTexts);
          }
          ''')
              return unique_texts
  
          # 使用示例
          text_contents = await get_unique_texts_js(page)
  
  
  
          return [types.TextContent(type="text", text=f"Text content of all elements: {text_contents}")]

• src/playwright_server/server.py:132-140 (schema)

  Tool schema definition in list_tools(): defines name, description, and empty inputSchema (no parameters required).

   types.Tool(
      name="playwright_get_text_content",
      description="Get the text content of all elements",
      inputSchema={
          "type": "object",
          "properties": {
          },
      }
  ),

• src/playwright_server/server.py:334-344 (registration)

  Registration of tool handlers in the tool_handlers dictionary, mapping 'playwright_get_text_content' to an instance of GetTextContentToolHandler.

  tool_handlers = {
      "playwright_navigate": NavigateToolHandler(),
      "playwright_screenshot": ScreenshotToolHandler(),
      "playwright_click": ClickToolHandler(),
      "playwright_fill": FillToolHandler(),
      "playwright_evaluate": EvaluateToolHandler(),
      "playwright_click_text": ClickTextToolHandler(),
      "playwright_get_text_content": GetTextContentToolHandler(),
      "playwright_get_html_content": GetHtmlContentToolHandler(),
      "playwright_new_session":NewSessionToolHandler(),
  }