Skip to main content
Glama
JaDi03

Browser Intelligence MCP

by JaDi03

Browser Intelligence MCP

一个模型上下文协议(MCP)服务器,为 AI 代理提供真实的浏览器能力: 截取屏幕截图、抓取结构化内容以及运行可视化页面测试。


概述

Browser Intelligence MCP 是一个使用 Node.js 和 TypeScript 构建的标准 MCP 服务器。 它提供了三个强大的工具,使 AI 代理能够通过由 Playwright 驱动的无头 Chromium 浏览器 与真实网页进行交互。

该服务器是按使用量计费的代理原生服务基础设施的演示组件。


Related MCP server: MCP Browser Screenshot Server

工具

工具

描述

take_screenshot

将任意 URL 的完整页面或视口截图捕获为 PNG 图像

scrape_page

从任意 URL 提取结构化内容(标题、描述、链接)

run_visual_test

对页面运行一组检查并返回通过/失败结果


环境要求

  • Node.js >= 22

  • npm >= 10


快速开始

# 1. Clone the repository
git clone https://github.com/your-org/browser-intelligence-mcp.git
cd browser-intelligence-mcp

# 2. Install dependencies
npm install

# 3. Install Playwright browsers
npx playwright install chromium

# 4. Copy environment variables
cp .env.example .env

# 5. Run in development mode
npm run dev

MCP 配置

添加到您的 MCP 客户端配置中(例如,Claude Desktop 的 claude_desktop_config.json):

{
  "mcpServers": {
    "browser-intelligence": {
      "command": "node",
      "args": ["dist/index.js"],
      "cwd": "/path/to/browser-intelligence-mcp"
    }
  }
}

脚本

命令

描述

npm run dev

以开发模式运行,支持热重载

npm run build

将 TypeScript 编译为 JavaScript

npm start

运行编译后的生产构建

npm run lint

运行 ESLint 检查


许可证

MIT

Install Server
A
license - permissive license
A
quality
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (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 Servers

View all related MCP servers

Related MCP Connectors

  • Generate images, GIFs, and PDFs from HTML, URLs, or templates — from your AI agent.

  • AI-powered browser automation — navigate, click, fill forms, and extract data from any website.

  • Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.

View all MCP Connectors

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/JaDi03/mcp-example'

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