# Chrome Browser Automation

> Use this tool when you need to automate browser interactions, perform semantic searches, or analyze web content with AI-driven capabilities. It solves problems such as automating web workflows, searching for similar content, and extracting data from web pages, and accepts inputs like URLs, search queries, and browser actions, outputting results like screenshots, extracted data, and search rankings. It is ideal for use cases involving web automation, content analysis, and intelligent browsing, providing a comprehensive interface for developers and applications to interact with web content programmatically.

Canonical page: https://skillsregistry.net/skills/hangwin-chrome  
JSON: https://api.skillsregistry.net/v1/skills/hangwin-chrome

## Description

This MCP server provides AI assistants with comprehensive browser automation and semantic search capabilities through Chrome extension integration, built by hangye using TypeScript with a monorepo architecture spanning native messaging, WebAssembly optimization, and Vue.js interfaces. The implementation offers advanced browser tools including intelligent element clicking, form filling, screenshot capture, keyboard simulation, and navigation utilities, combined with a vector search engine featuring AI-powered content indexing, semantic similarity matching using transformer models with ONNX runtime, and multi-language text processing capabilities. Built with Chrome Native Messaging for cross-platform communication, SIMD-accelerated WebAssembly for performance optimization, and comprehensive model caching with conditional initialization, it serves developers building AI-driven web automation workflows, teams requiring semantic search across browser content, and applications needing programmatic web interaction with intelligent element detection and content analysis capabilities.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/hangwin-chrome)
- **Repository:** <https://github.com/hangwin/mcp-chrome>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "hangwin-chrome"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hangwin-chrome` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hangwin-chrome/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
