browser-use
This gives Claude Desktop access to browser automation tools for web scraping, form filling, and more.
README
<picture> <source media="(prefers-color-scheme: dark)" srcset="./static/browser-use-dark.png"> <source media="(prefers-color-scheme: light)" srcset="./static/browser-use.png"> <img alt="Shows a black Browser Use Logo in light color mode and a white one in dark color mode." src="./static/browser-use.png" width="full"> </picture>
<h1 align="center">Enable AI to control your browser</h1>
<!-- Keep these links. Translations will automatically update with the README. --> Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文
🤖 Quickstart
With uv (Python>=3.11):
# We ship every day - use the latest version!
uv pip install browser-use
Download chromium using playwright's shortcut:
uvx playwright install chromium --with-deps --no-shell
Create a .env file and add your API key. Don't have one? Start with a free Gemini key.
GEMINI_API_KEY=
Run your first agent:
from browser_use import Agent, ChatGoogle
from dotenv import load_dotenv
load_dotenv()
agent = Agent(
task="Find the number of stars of the browser-use repo",
llm=ChatGoogle(model="gemini-flash-latest"),
# browser=Browser(use_cloud=True), # Uses Browser-Use cloud for the browser
)
agent.run_sync()
Check out the library docs and cloud docs for more settings.
Stealth Browser Infrastructure
Want to bypass Cloudflare, or any other anti-bot protection?
Simply go to Browser Use Cloud grab a BROWSER_USE_API_KEY and use the use_cloud parameter.
from browser_use import Agent, Browser, ChatOpenAI
# Use Browser-Use cloud browser service
browser = Browser(
use_cloud=True, # Automatically provisions a cloud browser
)
agent = Agent(
task="Your task here",
llm=ChatOpenAI(model='gpt-4.1-mini'),
browser=browser,
)
Demos
Task: Add grocery items to cart, and checkout.
<br/><br/>
Task: Read my CV & find ML jobs, save them to a file, and then start applying for them in new tabs, if you need help, ask me.
https://github.com/user-attachments/assets/171fb4d6-0355-46f2-863e-edb04a828d04
<br/><br/>
See more examples and give us a star!
<br/><br/>
MCP Integration
This gives Claude Desktop access to browser automation tools for web scraping, form filling, and more. See the MCP docs.
{
"mcpServers": {
"browser-use": {
"command": "uvx",
"args": ["browser-use[cli]", "--mcp"],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}
<div align="center">
Tell your computer what to do, and it gets it done.
<img src="https://github.com/user-attachments/assets/06fa3078-8461-4560-b434-445510c1766f" width="400"/>
</div>
<div align="center"> Made with ❤️ in Zurich and San Francisco </div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器