Skip to main content
Glama
ma-pony

mcp-playwright

by ma-pony
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
create_browser_sessionA
创建新的浏览器会话

Args:
    browser_type: 浏览器类型 (chromium, firefox, webkit)
    headless: 是否无头模式
    viewport_width: 视口宽度
    viewport_height: 视口高度
    timeout: 默认超时时间(毫秒)
close_browser_sessionA

关闭当前浏览器会话

navigate_to_urlC
导航到指定URL

Args:
    url: 目标URL
    wait_until: 等待条件 (load, domcontentloaded, networkidle)
click_elementC
点击页面元素

Args:
    selector: CSS选择器或XPath
    timeout: 超时时间(毫秒)
    force: 强制点击
fill_inputA
填写输入框

Args:
    selector: CSS选择器或XPath
    text: 要输入的文本
    timeout: 超时时间(毫秒)
wait_for_selectorB
等待元素出现

Args:
    selector: CSS选择器或XPath
    timeout: 超时时间(毫秒)
    state: 元素状态 (attached, detached, visible, hidden)
get_text_contentC
获取元素文本内容

Args:
    selector: CSS选择器或XPath
    timeout: 超时时间(毫秒)
get_element_attributeC
获取元素属性值

Args:
    selector: CSS选择器或XPath
    attribute: 属性名
    timeout: 超时时间(毫秒)
get_page_titleA

获取页面标题

get_page_urlA

获取当前页面URL

take_screenshotC
截取页面截图

Args:
    path: 保存路径(可选)
    full_page: 是否截取整页
    quality: 图片质量(1-100)
execute_javascriptC
执行JavaScript代码

Args:
    code: JavaScript代码

Prompts

Interactive templates invoked by user choice

NameDescription
web_automation_prompt 网页自动化任务提示模板 Args: task: 要执行的任务描述 url: 目标网站URL

Resources

Contextual data attached and managed by the client

NameDescription
get_session_status获取当前会话状态
get_browser_health获取浏览器管理器健康状态
get_tools_help获取工具使用帮助
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.3/5.0

Scored across 12 tools

Disambiguation5/5

Each tool targets a distinct browser action: clicking, filling, navigating, screenshotting, etc. No two tools have overlapping functionality.

Naming Consistency5/5

All tools follow a consistent verb_noun snake_case pattern (e.g., click_element, fill_input, get_page_title). No deviations.

Tool Count5/5

12 tools cover the essential browser automation operations without being excessive. The count is well-scoped for the domain.

Completeness4/5

Core workflows like navigation, input, clicking, and screenshots are present. Minor gaps like scrolling or hover are absent but can be worked around.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources