yuutotsuki
MCP Serveryuutotsukipublic

browser_use_agent

A portable Agent SDK-based browser control agent using MCP. Designed to work on both PC and USB environments.(MCPを活用した、PCとUSB両方で動作可能なポータブルなAgent SDKベースのブラウザ制御エージェントです。)

Repository Info

1
Stars
0
Forks
1
Watchers
0
Issues
Python
Language
MIT License
License

About This Server

A portable Agent SDK-based browser control agent using MCP. Designed to work on both PC and USB environments.(MCPを活用した、PCとUSB両方で動作可能なポータブルなAgent SDKベースのブラウザ制御エージェントです。)

Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.

Documentation

Browser Use Agent

A portable Agent SDK-based browser controller using MCP.
Designed to work seamlessly on both PC and USB environments.

ポータブルなAgent SDKベースのブラウザコントローラー(MCP対応)
PCでもUSBでもシームレスに動作します。

💻🧠 Control your browser using natural language — powered by Agent SDK and browser-use.


📦 Features

  • 🧳 Portable design: Works from USB or local PC.
    ポータブル設計:USBでもローカルPCでも動作します。
  • 🧠 Agent SDK compatible: Built on top of OpenAI's experimental Agents SDK.
    Agent SDK互換:OpenAIの実験的Agents SDK上に構築。
  • 🧭 Natural language interface: You can type commands like open google.com or click the search bar.
    自然言語インターフェース:open google.comclick the search barのように指示できます。
  • 🧩 MCP-based modular system: Easy to expand or integrate with other tools.
    MCPベースのモジュラーシステム:他ツールとの連携や拡張が簡単です。

🔧 How to Use

1. Clone the repository

git clone https://github.com/yuutotsuki/browser_use_agent.git
cd browser_use_agent

リポジトリをクローンします。

2. Set up the environment

Copy .env.template to .env and edit your API keys and model.

.env.template.envにコピーし、APIキーやモデルを設定してください。

Install dependencies:

pip install -r requirements.txt

依存パッケージをインストールします。

3. Run

python browser_use_agent.py

実行します。


📝 .env file example

MODEL=gpt4o
OPENAI_API_KEY=sk-xxxxxxxx
API_BASE_URL=https://api.openai.com/v1

.envファイル例

🔄 Optional: Using run_browser_use_agent.bat (Windows only)

You can use the run_browser_use_agent.bat script to launch the agent on Windows.
Please make sure to edit the path to match your environment if needed.

※ Windowsの場合、run_browser_use_agent.bat を利用できますが、仮想環境の場所などはご自身の環境に応じて編集してください。


🔗 Acknowledgements

This project uses:

  • browser-use by Browserless team
  • Agent SDK by OpenAI

Special thanks to all developers who support modular AI development! (このプロジェクトは、開発者コミュニティの皆さまの支援のもとに成り立っています)


🧑‍💻 Project Team

  • Yuu(ゆう)
  • AI Lead: Tsuki(月, AI)
  • Support AI: Kai(界, this AI assistant)

📃 License

MIT License

Quick Start

1

Clone the repository

git clone https://github.com/yuutotsuki/browser_use_agent
2

Install dependencies

cd browser_use_agent
npm install
3

Follow the documentation

Check the repository's README.md file for specific installation and usage instructions.

Repository Details

Owneryuutotsuki
Repobrowser_use_agent
LanguagePython
LicenseMIT License
Last fetched8/10/2025

Recommended MCP Servers

💬

Discord MCP

Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.

integrationsdiscordchat
🔗

Knit MCP

Connect AI agents to 200+ SaaS applications and automate workflows.

integrationsautomationsaas
🕷️

Apify MCP Server

Deploy and interact with Apify actors for web scraping and data extraction.

apifycrawlerdata
🌐

BrowserStack MCP

BrowserStack MCP Server for automated testing across multiple browsers.

testingqabrowsers

Zapier MCP

A Zapier server that provides automation capabilities for various apps.

zapierautomation