Skip to main content
Glama

steel-tester

内网 Steel Browser 工具:CLI + MCP。browser_navigate 对齐 cursor-ide-browser:默认复用上次视图并打开 URL。

依赖

  • Node.js >= 22.13

  • playwright-core(CDP,不下载 Chromium)

  • @modelcontextprotocol/sdk + zod(MCP)

  • 可访问的内网 Steel(STEEL_BROWSER_API_URL

Related MCP server: Playwright MCP Server

安装

npm install -g steel-tester
# 或
npm install -D steel-tester

配置

优先级:--api-url / --cdp-url > 环境变量 > 当前目录 .env

export STEEL_BROWSER_API_URL=http://<host>:3000/v1
# 可选:STEEL_CDP_URL=ws://10.0.0.12:3000/

CLI

npx steel-tester open --url=https://www.baidu.com
npx steel-tester open --url=https://www.baidu.com --new-tab --screenshot
npx steel-tester open --url=https://www.baidu.com --view-id=<sessionId>
npx steel-tester open --url=https://www.baidu.com --clean

stdout:

{
  "viewId": "<uuid>",
  "sessionId": "<uuid>",
  "cdpUrl": "ws://<ip>:3000/",
  "url": "https://www.baidu.com/",
  "title": "百度一下"
}

MCP

npx steel-tester mcp
{
  "mcpServers": {
    "steel-tester": {
      "command": "npx",
      "args": ["-y", "steel-tester", "mcp"],
      "env": {
        "STEEL_BROWSER_API_URL": "http://<host>:3000/v1"
      }
    }
  }
}

工具:browser_navigate

参数

说明

url

要打开的 URL(必填)

viewId

目标 session id;省略则用上次视图

newTab

true 时新建标签再导航

take_screenshot_afterwards

true 时导航后截图

clean

true 时先释放全部 live session

开发

npm install
npm run build
npm run steel-tester -- open --url=https://example.com --clean
A
license - permissive license
Not graded
quality - not tested
C
maintenance

Maintenance

0Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Exposes Steel Browser automation over HTTP, providing MCP clients with tools for browser control, page interaction, screenshots, and session management.
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to control and interact with a Chrome browser via MCP, providing tools for navigation, screenshots, clicking, form filling, content extraction, and tab management.
  • A
    license
    Not graded
    quality
    B
    maintenance
    An MCP server that gives AI clients a Steel-managed Chromium browser to read pages that block plain fetch, take screenshots, and interact with sites via clicking, typing, and form filling, with explicit browser sessions and access to the accessibility tree or markdown.
    MIT

View all related MCP servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ywf2016/steel-tester'

If you have feedback or need assistance with the MCP directory API, please join our Discord server