Direct browser control via Chrome DevTools Protocol. Two modes available:
- Skill Mode - CLI tool for Claude Code agents (
browsingskill) - MCP Mode - Ultra-lightweight MCP server for any MCP client
- Zero dependencies - Built-in WebSocket, no npm install needed
- Idiotproof API - Tab index syntax (
0,1,2) instead of WebSocket URLs - Platform-agnostic -
chrome-ws startworks on macOS, Linux, Windows - 17 commands covering all browser automation needs
- Complete documentation with real-world examples
/plugin marketplace add obra/superpowers-marketplace
/plugin install superpowers-chrome@superpowers-marketplacecd ~/.claude/plugins/cache/superpowers-chrome/skills/browsing
./chrome-ws start # Launch Chrome
./chrome-ws new "https://example.com" # Create tab
./chrome-ws navigate 0 "https://google.com"
./chrome-ws fill 0 "textarea[name=q]" "test"
./chrome-ws click 0 "button[name=btnK]"- Setup:
start(auto-detects platform) - Tab management:
tabs,new,close - Navigation:
navigate,wait-for,wait-text - Interaction:
click,fill,select - Extraction:
eval,extract,attr,html - Export:
screenshot,markdown - Raw protocol:
raw(full CDP access)
Ultra-lightweight MCP server with a single use_browser tool. Perfect for minimal context usage.
Add to Claude Desktop config:
{
"mcpServers": {
"chrome": {
"command": "node",
"args": [
"/path/to/superpowers-chrome/mcp/dist/index.js"
]
}
}
}{
"action": "navigate",
"payload": "https://example.com"
}See mcp/README.md for complete documentation.
Use Skill Mode when:
- Working with Claude Code agents
- Need full CLI control with 17 commands
Use MCP Mode when:
- Using Claude Desktop or other MCP clients
- Want minimal context usage (single tool)
Use Playwright MCP when:
- Need fresh browser instances
- Complex automation with screenshots/PDFs
- Prefer higher-level abstractions
- SKILL.md - Complete skill guide
- EXAMPLES.md - Real-world examples
- chrome-ws README - Tool documentation
MIT