playwright_navigate
Automate web browser navigation to a specified URL; creates a new session if none exists. Simplify web interactions with Playwright Server MCP‘s browser control capabilities.
Instructions
浏览器导航到指定网址，如果没有活跃的浏览器会话，会自动创建一个新会话
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | 需要访问的网址，如不包含http或https前缀将自动添加https:// |
Implementation Reference
- The core handler function that executes the playwright_navigate tool: checks for active session, navigates to the provided URL using page.goto(), fetches page text content, and returns success message.async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]: logger.info("开始浏览器导航操作") if not self._sessions: logger.warning("没有活跃的会话，正在创建新会话") await NewSessionToolHandler().handle("",{}) # return [types.TextContent(type="text", text="No active session. Please create a new session first.")] try: page = self.get_page() url = arguments.get("url") if not url.startswith("http://") and not url.startswith("https://"): url = "https://" + url logger.info(f"正在导航到 URL: {url}") await page.goto(url) logger.debug(f"导航完成, 当前URL: {page.url}") text_content=await GetTextContentToolHandler().handle("",{}) return [types.TextContent(type="text", text=f"Navigated to {url}\npage_text_content[:200]:\n\n{text_content[:200]}")] except Exception as e: logger.error(f"导航失败: {str(e)}", exc_info=True) return [types.TextContent(type="text", text=f"导航失败: {str(e)}")]
- Tool metadata including name, description, and inputSchema defining the 'url' parameter for the playwright_navigate tool.class NavigateToolHandler(ToolHandler): name = "playwright_navigate" description = "浏览器导航到指定网址，如果没有活跃的浏览器会话，会自动创建一个新会话" inputSchema = [ Property(name="url", typ="string", description="需要访问的网址，如不包含http或https前缀将自动添加https://") ]
- src/playwright_server/server.py:43-55 (registration)Instantiates NavigateToolHandler and registers it in tool_handler_list and tool_handlers dict, which is used in list_tools() and call_tool() for MCP server.tool_handler_list = [ NavigateToolHandler(), # ScreenshotToolHandler(), EvaluateToolHandler(), GetTextContentToolHandler(), GetHtmlContentToolHandler(), NewSessionToolHandler(), ActionToolHandler() ] # 根据每个处理程序的 name 属性创建字典 tool_handlers = {handler.name: handler for handler in tool_handler_list}
- The to_tool classmethod in base ToolHandler converts handler metadata to MCP Tool object, used during registration in list_tools().def to_tool(cls) -> types.Tool: return types.Tool( name=cls.name, description=cls.description, inputSchema={ "type": "object", "properties": { property.name: { "type": property.typ, "description": property.description } for property in cls.inputSchema }, "required": [property.name for property in cls.inputSchema if property.required] } )
- src/playwright_server/server.py:98-108 (registration)MCP server endpoint that lists tools by calling to_tool() on registered handlers, exposing playwright_navigate.@server.list_tools() async def handle_list_tools() -> list[types.Tool]: """ List available tools. Each tool specifies its arguments using JSON Schema validation. """ logger.debug("处理 list_tools 请求") return [ tool_handler.to_tool() for tool_handler in tool_handlers.values() ]