playwright_new_session

Create and manage new browser sessions to open windows and optionally navigate to specified URLs using browser automation capabilities.

Instructions

创建新的浏览器会话，打开一个浏览器窗口并可选择性地访问指定网址

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	No	需要访问的初始网址，可选参数，不填则只打开浏览器

Implementation Reference

src/playwright_server/tools/handles.py:52-86 (handler)

NewSessionToolHandler class implements the core logic for the 'playwright_new_session' tool, launching a new Chromium browser instance, creating a page, managing sessions, and optionally navigating to a URL.

class NewSessionToolHandler(ToolHandler):
    name = "playwright_new_session"
    description = "创建新的浏览器会话，打开一个浏览器窗口并可选择性地访问指定网址"
    inputSchema = [
        Property(name="url", typ="string", description="需要访问的初始网址，可选参数，不填则只打开浏览器", required=False)
    ]
    
    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
        logger.info("开始创建新的浏览器会话")
        try:
            self._playwright = await async_playwright().start()
            logger.debug("Playwright 实例已创建")
            
            browser = await self._playwright.chromium.launch(headless=False)
            logger.debug("浏览器已启动")
            
            page = await browser.new_page()
            logger.debug("新页面已创建")
            
            session_id = str(uuid.uuid4())
            self._sessions[session_id] = {"browser": browser, "page": page}
            logger.info(f"会话已创建，ID: {session_id}")
            
            url = arguments.get("url")
            if 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}")
            return [types.TextContent(type="text", text="succ")]
        except Exception as e:
            logger.error(f"创建会话失败: {str(e)}", exc_info=True)
            return [types.TextContent(type="text", text=f"创建会话失败: {str(e)}")]

src/playwright_server/tools/handles.py:55-57 (schema)

Defines the input schema for the tool, with an optional 'url' parameter of type string.

inputSchema = [
    Property(name="url", typ="string", description="需要访问的初始网址，可选参数，不填则只打开浏览器", required=False)
]

src/playwright_server/server.py:43-54 (registration)

Registers the NewSessionToolHandler instance in tool_handler_list and creates tool_handlers dictionary mapped by name, used by MCP server for list_tools() and call_tool().

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}

src/playwright_server/server.py:11-11 (registration)

Imports the NewSessionToolHandler class required for registration.

from playwright_server.tools.handles import NavigateToolHandler, ScreenshotToolHandler, EvaluateToolHandler, GetTextContentToolHandler, GetHtmlContentToolHandler, NewSessionToolHandler

src/playwright_server/tools/base.py:22-39 (helper)

ToolHandler base class method to_tool() converts the handler's name, description, and inputSchema into MCP Tool object for registration in list_tools().

@classmethod
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]
        }
    )

Playwright Server MCP