Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
作者提供的说明(英文原文)
Scrape any website, extract structured data, and collect web content at scale with AI agents
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"scrapfly-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add mcp -- npx -y scrapfly-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"scrapfly-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"scrapfly-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过域名 mcp.scrapfly.io 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.0.0)于11个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Browser Use, Chrome DevTools MCP, MCP Server Browser
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
MCP server for Chrome DevTools
MCP server for browser use access
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Give your AI real-time access to any website
🌐 Landing Page • 📖 Documentation • 🎮 Live Demo • 🔑 Get API Key
| Remote server | https://mcp.scrapfly.io/mcp (streamable HTTP, nothing to install) |
| Self-hosted | Go binary (stdio or -http) or the Docker image of this repo, see Self-Hosted below |
| stdio-only clients | npx mcp-remote https://mcp.scrapfly.io/mcp |
| Authentication | OAuth2 sign-in on the remote server, or a Scrapfly API key (SCRAPFLY_API_KEY, Authorization: Bearer ) |
| Tools | 62: web scraping (5), account (2), Cloud Browser sessions (9), page interaction (17), WebMCP (2), credential vaults (15), alerts (12). Full list under Available Tools below. |
Add it to any MCP client:
{
"mcpServers": { "scrapfly": { "type": "http", "url": "https://mcp.scrapfly.io/mcp" } } }
Tools that fetch pages need no setup beyond the key: web_get_page (quick fetch), web_scrape (full control: JS rendering, proxy pool, country, extraction) and screenshot.
The Scrapfly MCP Server connects your AI assistants to live web data through the Model Context Protocol. Transform your AI from being limited by training data to having real-time access to any website.
| Capability | Description |
|---|---|
| 🌐 Scrape Live Data | Pull current prices, listings, news, or any webpage content in real-time |
| 🛡️ Bypass Anti-Bot Systems | Automatically handle CAPTCHAs, proxies, JavaScript rendering, and rate limits |
| ⚡ Extract Structured Data | Parse complex websites into clean JSON using AI-powered extraction |
| 📸 Capture Screenshots | Take visual snapshots of pages or specific elements for analysis |
Built on battle-tested infrastructure used by thousands of developers:
📖 Learn more: Why Scrapfly MCP?
Click one of the buttons below to install the MCP server in your preferred IDE:
Works with most MCP-compatible tools:
{
"servers": { "scrapfly-cloud-mcp": { "type": "http", "url": "https://mcp.scrapfly.io/mcp" } } }
For tools that require a local process:
{
"mcpServers": { "scrapfly": { "command": "npx", "args": [ "mcp-remote", "https://mcp.scrapfly.io/mcp" ] } } }
VS Code
Follow the VS Code MCP guide or use the CLI:
code --add-mcp '{"name":"scrapfly-cloud-mcp","type":"http","url":"https://mcp.scrapfly.io/mcp"}'
After installation, Scrapfly tools will be available in GitHub Copilot Chat.
📖 Full guide: VS Code Integration
VS Code Insiders
code-insiders --add-mcp '{"name":"scrapfly-cloud-mcp","type":"http","url":"https://mcp.scrapfly.io/mcp"}'
📖 Full guide: VS Code Integration
Visual Studio
scrapfly-cloud-mcphttp/ssehttps://mcp.scrapfly.io/mcp📖 Full guide: Visual Studio MCP documentation
Cursor
Cursor Settings → MCP → Add new MCP Server📖 Full guide: Cursor Integration
Claude Code
Use the Claude Code CLI:
claude mcp add scrapfly-cloud-mcp --url https://mcp.scrapfly.io/mcp
📖 Full guide: Claude Code Integration
Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": { "scrapfly": { "command": "npx", "args": ["mcp-remote", "https://mcp.scrapfly.io/mcp"] } } }
📖 Full guide: Claude Desktop Integration
Cline
Add to your Cline MCP settings:
{
"scrapfly-cloud-mcp": { "type": "http", "url": "https://mcp.scrapfly.io/mcp" } }
📖 Full guide: Cline Integration
Windsurf
Follow the Windsurf MCP documentation using the standard configuration.
📖 Full guide: Windsurf Integration
Zed
Add to your Zed settings:
{
"context_servers": { "scrapfly-cloud-mcp": { "type": "http", "url": "https://mcp.scrapfly.io/mcp" } } }
📖 Full guide: Zed Integration
OpenAI Codex
Create or edit ~/.codex/config.toml:
[mcp_servers.scrapfly-cloud-mcp]
url = "https://mcp.scrapfly.io/mcp"
📖 More info: Codex MCP documentation
Gemini CLI
Follow the Gemini CLI MCP guide using the standard configuration.
OpenCode
Add to ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json", "mcp": { "scrapfly-cloud-mcp": { "type": "http", "url": "https://mcp.scrapfly.io/mcp", "enabled": true } } }
📖 More info: OpenCode MCP documentation
The Scrapfly MCP Server exposes 62 tools in seven groups. Most tasks need only the first group.
Stateless, one call per page.
| Tool | Description | Use Case |
|---|---|---|
scraping_instruction_enhanced | Cheat-sheet of the scraping options | Optional, when the right options are unclear |
web_get_page | Quick page fetch with smart defaults | Simple scraping tasks |
web_scrape | Full control: headers, JS rendering, country, proxy pool, extraction | Complex scraping, login flows |
screenshot | One-shot PNG of a URL | Visual analysis, monitoring |
check_if_blocked | Decide whether a scrape result is a block page | Retry or escalate the proxy pool |
| Tool | Description |
|---|---|
info_account | Subscription plan, API credit usage, concurrency |
info_api_key | The API key this server is authenticated with |
A stateful real browser, kept between calls.
| Tool | Description |
|---|---|
cloud_browser_open | Start a session at a URL |
browser_unblock | Same, through the anti-bot bypass first |
cloud_browser_navigate | Load a new URL in the open session |
cloud_browser_sessions | List active sessions |
cloud_browser_close | Close the session |
cloud_browser_screenshot | PNG of the session, optionally of a CSS selector |
| cloud_browser_eval | Run JavaScript an
只显示了开头部分;其余内容请在仓库中阅读