Browseract

Created By

BrowserActa month ago

BrowserAct MCP Server is a standardized service that lets MCP Clients interact with the BrowserAct platform through the Model Context Protocol (MCP). With it, MCP Clients can: Discover and execute browser automation workflows as MCP Tools Read outputs (results, files) and access related data storage Trigger real-world actions via natural language (e.g., send messages, create tasks, update records) Key Features 1. Multi-Scenario Support: Enables MCP Clients to run targeted tasks or complex searches across different applications 2. Natural Language Interaction: Describe what you need—no complex code or commands 3. Unlimited Tool Exposure: One MCP Server can expose unlimited MCP Tools 4. Multi-Client Compatibility: Works with Claude, ChatGPT, OpenAI Agent Builder, and other MCP-compatible clients

# MCP

# AI

Overview Content Tools Comments

Content

BrowserAct API Demo Collection

AI Web Scraper & Automation - Any Site, No Code, Zero Limits, Reliable Data

This repository contains comprehensive API demo code for BrowserAct, an AI-powered web scraping and automation platform. The demos showcase how to integrate BrowserAct's AI-Workflow capabilities into your applications using multiple programming languages.

🚀 Quick Start

Choose your preferred language and get started in minutes:

Language	Workflow API	Quick Start
Python	Workflow-Python	`cd Workflow-Python && python 1.run_task.py`
Java	Workflow-Java	`cd Workflow-Java && mvn exec:java -Dexec.mainClass="com.browseract.workflow.demo.RunTask"`
Node.js	Workflow-NodeJs	`cd Workflow-NodeJs && node 1.runTask.js`

📁 Project Structure

browseract-api-demos/
├── Workflow-Python/       # Python Workflow API demos
├── Workflow-Java/         # Java Workflow API demos
├── Workflow-NodeJs/       # Node.js Workflow API demos
├── .gitignore             # Git ignore rules
└── README.md              # This file

🎯 What is BrowserAct?

BrowserAct is an AI-powered web scraping and automation platform that provides two core capabilities:

🔄 AI-Workflow

Predefined Templates: Use pre-built workflows for common scraping tasks
Custom Workflows: Create your own automation sequences
Batch Processing: Handle multiple URLs and data sources efficiently

📚 API Capabilities

Workflow API Endpoints

Endpoint	Method	Description
`/v2/workflow/run-task`	POST	Start a new workflow task
`/v2/workflow/stop-task`	PUT	Permanently terminate a task
`/v2/workflow/get-task`	GET	Get detailed task information
`/v2/workflow/get-task-status`	GET	Get task status only
`/v2/workflow/list-tasks`	GET	List all tasks
`/v2/workflow/list-workflows`	GET	List all workflows
`/v2/workflow/get-workflow`	GET	Get workflow details

🛠 Language Support

Python

Version: Python 3.8+
Dependencies: requests for HTTP requests
Features: Simple, readable code with comprehensive error handling
Best for: Quick prototyping and data science workflows

Java

Version: Java 8+
Build Tool: Maven
Dependencies: Jackson for JSON processing, HttpURLConnection for HTTP requests
Features: Enterprise-grade code with proper package structure
Best for: Enterprise applications and microservices

Node.js

Version: Node.js 14+
Dependencies: Built-in https module
Features: Lightweight, async-first approach
Best for: Web applications and serverless functions

🔧 Configuration

Before running any examples, you'll need:

API Key: Get your API key from BrowserAct Integrations
Workflow ID (for Workflow API): Get your workflow ID from Workflow List

Update the configuration in each example file:

Replace "app-abcdefghijklmn" with your actual API key
Replace 1234567890 with your actual workflow ID

🔒 Security Best Practices

Important: The examples use placeholder API keys for demonstration purposes. In production:

Never hardcode API keys in your source code
Use environment variables or secure configuration files
Keep your API keys confidential and rotate them regularly

Environment Variable Examples

# Python
import os
authorization = os.getenv("BROWSERACT_API_KEY")

// Java
String authorization = System.getenv("BROWSERACT_API_KEY");

// Node.js
const authorization = process.env.BROWSERACT_API_KEY;

📖 Documentation

API Documentation: BrowserAct API Docs
Workflow API: Workflow API Reference

🤝 Support

Discord Community: Join our Discord
Email Support: support@browseract.com
GitHub Issues: Report bugs or request features

📄 License

This demo code is provided as-is for educational and development purposes under the MIT License.

🌟 Features

Multi-language Support: Python, Java, and Node.js implementations
Complete API Coverage: All BrowserAct API endpoints included
Production Ready: Enterprise-grade code with proper error handling
Easy to Use: Simple examples that can be run immediately
Well Documented: Comprehensive README files for each language
Modern Standards: Follows best practices for each language

Ready to get started? Choose your language above and dive into the examples! 🚀

Visit BrowserAct to learn more about our AI-powered web scraping platform.

Server Config

{
  "mcpServers": {
    "browseract": {
      "url": "<BROWSERACT_MCP_SERVER_URL>",
      "headers": {
        "Authorization": "Bearer <BROWSERACT_API_KEY>"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

Serper MCP ServerA Serper MCP Server

Amap Maps高德地图官方 MCP Server

AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

DeepChatYour AI Partner on Desktop

Tavily Mcp

WindsurfThe new purpose-built IDE to harness magic