browserwing-executor

Automate browser control from Go via HTTP APIs and MCP integration.

1.4k|128|Updated Dec 10, 2025
One-click install
npx skills add https://github.com/browserwing/browserwing --skill browserwing-executor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browserwing-executor
Source: https://github.com/browserwing/browserwing/tree/main
Command: npx skills add https://github.com/browserwing/browserwing --skill browserwing-executor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

BrowserWing Executor provides a Go-based interface to automate browser tasks over HTTP, enabling MCP integration for AI agents and automation pipelines.

Core Features & Use Cases

  • Navigation & Interaction: navigate to URLs, click, type, select, and hover on web pages.
  • Data Extraction & Accessibility: extract text/attributes and obtain accessibility snapshots to guide automation.
  • Batch & MCP Integration: execute sequences of actions and expose tools via MCP for AI agents, RPA, and QA tasks.
  • Use Case: Build an AI-assisted workflow that visits a site, logs in, and scrapes key data, then exports results to an MCP command or Skills file.

Quick Start

Install the package, initialize the BrowserManager, create an Executor, and perform a simple navigate to https://example.com.

Frequently Asked Questions about browserwing-executor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser interactions from Go code?

Browser automation from Go uses HTTP APIs to control navigation, clicks, typing, and element selection on web pages. BrowserWing Executor provides a Go interface that connects to a browser over HTTP, letting you script interactions programmatically without manual browser control.

Can I use browser automation with MCP integration for AI agents?

Yes. MCP integration exposes browser automation tools that AI agents can invoke directly. BrowserWing Executor registers actions like navigation and data extraction as MCP tools, enabling agents to control browsers and extract information as part of automated workflows.

What can I extract from web pages during automation?

During automation, you can extract text and HTML attributes from page elements and obtain accessibility snapshots. These snapshots provide semantic structure that guides subsequent interactions, supporting both data capture and intelligent navigation through page content.

How do I execute multiple browser actions in sequence?

Batch execution chains multiple actions—navigate, click, type, select—into a single sequence. BrowserWing Executor processes these batched operations efficiently, reducing overhead and enabling complex workflows like login-then-scrape scenarios.

Does browser automation work for testing and data extraction workflows?

Browser automation supports both QA testing and data extraction. You can log in to sites, interact with dynamic content, and capture results. BrowserWing Executor handles these workflows through a unified Go API, making it suitable for automated testing, RPA, and web scraping tasks.

What does semantic-tree support enable in browser automation?

Semantic-tree support structures page elements hierarchically, allowing automation logic to navigate and interact with pages based on meaning rather than brittle selectors. This improves robustness when page layouts change and simplifies reasoning about element relationships during interaction sequences.