// MCP TOOL REFERENCE

MCP PLAYWRIGHT TOOLS

12 tools from the Mcp Playwright MCP Server, categorised by risk level.

// ALL 12 MCP PLAYWRIGHT TOOLS

READ 5 tools

Read get_element_attribute 获取元素属性值 Read get_page_title 获取页面标题 Read get_page_url 获取当前页面URL Read get_text_content 获取元素文本内容 Read take_screenshot 截取页面截图

DESTRUCTIVE 1 tools

Destructive close_browser_session 关闭当前浏览器会话

EXECUTE 6 tools

Execute execute_javascript 执行JavaScript代码 Execute navigate_to_url 导航到指定URL Execute wait_for_selector 等待元素出现 Execute click_element 点击页面元素 Execute create_browser_session 创建新的浏览器会话 Execute fill_input 填写输入框

// FAQ

How many tools does the Mcp Playwright MCP server have? +

The Mcp Playwright MCP server exposes 12 tools across 3 categories: Read, Destructive, Execute.

How do I enforce policies on Mcp Playwright tools? +

Route the Mcp Playwright server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Mcp Playwright tools fall into? +

Mcp Playwright tools are categorised as Read (5), Destructive (1), Execute (6). Each category has a recommended default policy.

Enforce policy on every Mcp Playwright tool call.

Start from Mcp Playwright, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.