Browser Use
PluginBrowser Use's official plugin: connects the Browser Use MCP so Claude can drive your local Chrome or a cloud browser to browse, extract data, fill forms, test sites and take screenshots. Needs uv; cloud browsers need sign-in or an API key.
browser-use
Give Claude Code a real browser — your Chrome or a Browser Use Cloud browser — powered by the Browser Use CLI 3.0.
How it works
The plugin registers the Browser Use MCP server, self-installing and always current:
.mcp.jsonlaunchesuvx browser-use@latest --cli-mcp— uv fetches the latest stable release from PyPI on first use (the CLI bundles browser-harness as a pinned dependency, so that's everything) and re-resolves the version on each session start.- The server exposes the CLI 3.0 surface:
browser_exec(drive the browser with Python — clicks, navigation, DOM extraction, raw CDP) andbrowser_screenshot, and ships its full usage instructions as native MCP server instructions, version-matched to the running release.
There is nothing here to sync when the library changes: no code, no skill text — just the launch config.
Install
claude plugin marketplace add browser-use/plugins
claude plugin install browser-use@browser-use
Requires uv (curl -LsSf https://astral.sh/uv/install.sh | sh). Then just ask Claude to do something on the web, e.g. "open Hacker News and summarize the top 5 Show HN posts." For local Chrome control, allow remote debugging when Chrome prompts (chrome://inspect/#remote-debugging → "Allow remote debugging for this browser instance"). Cloud browsers are optional and authenticate via browser-use auth login or BROWSER_USE_API_KEY.
관련 리소스
Browser Use
SkillControls your local Chrome over CDP to navigate, click, type, take screenshots and scrape data, reusing logged-in sessions. Official browser-use skill; install the browser-use CLI with uv first.
browser-use/browser-use118k
agent-browser
PluginBrowser automation plugin from Vercel Labs: agents drive Chrome through accessibility tree snapshots and element refs to navigate, click, fill forms and take screenshots, for web testing and exploratory QA. Install the agent-browser CLI first (npm, Homebrew or Cargo).
vercel-labs/agent-browser44.1kagent-browser
CLIBrowser automation CLI built for AI agents in native Rust: open pages, click and fill forms by refs from accessibility tree snapshots, read text and take screenshots, with compact snapshots and output limits to save context. From Vercel Labs; reuses local Chrome or installs one.
vercel-labs/agent-browser44.1k
Dev Browser
SkillLets coding agents control real Chrome with short Puppeteer scripts, with named pages that keep state across calls, accessibility-tree snapshots and screenshots for self-testing web changes. Install the dev-browser CLI globally first; macOS and glibc Linux only.
SawyerHood/dev-browser6.7k
ExecuteAutomation Playwright MCP Server
MCPCommunity Playwright browser automation MCP from ExecuteAutomation (not Microsoft's official one): navigate, click, fill forms, screenshot and scrape page text, plus send HTTP requests, assert network responses and record actions into test code, with 143 device emulations built in.
executeautomation/mcp-playwright5.7kBrowser Use MCP
MCPLocal MCP server built into Browser Use: lets agents navigate, click, type and extract page content, or hand multi-step tasks to the built-in browser agent. Bring your own OpenAI or Anthropic API key.
browser-use/browser-use118k