Productivity and Automation
Browser and computer automation — AI agent skills
Drive a real machine. A focused slice of the Productivity and Automation category: every indexed skill that fits browser and computer automation, scored on the same axis across Claude Skills, MCP servers, Cursor rules, Custom GPTs, n8n, and the rest.
- Indexed
- 16
- Avg score
- 6.7
- Top platform
- MCP Servers 12
- Top industry
- Software and SaaS 2
Top picks for browser and computer automation
Playwright MCP
Microsoft's official Playwright MCP server — lets LLMs drive a browser through structured accessibility snapshots rather than screenshots.
Filesystem MCP Server
Node.js reference MCP server for secure filesystem operations — read, write, search, and manage files with configurable access controls.
Peekaboo
High-fidelity macOS screen capture, GUI automation, and natural-language agent orchestration via CLI or MCP server.
Auto Browser
Give your AI agent a real browser with human-in-the-loop oversight, reusable login profiles, approvals, and audit trails.
Browserbase MCP Server
MCP server enabling LLMs to interact with web pages, extract information, and perform automated actions using Browserbase and Stagehand.
agent-device
CLI tool that lets coding agents automate mobile, TV, and desktop apps through token-efficient accessibility snapshots and perform UI interactions with real-time evidence capture.
Apify MCP Server
MCP server enabling AI agents to use Apify Actors for web scraping, data extraction, and automation across social media, search engines, maps, and e-commerce sites.
DeepCamera
Deploy AI skills on edge cameras with VLM scene analysis, YOLO object detection, and local privacy-preserving depth mapping—all running locally without cloud uploads.
PhoneClaw
Android automation app that generates and runs on-device workflows using ClawScript, a JavaScript-based scripting language with vision-assisted UI control and multi-app orchestration.
OpenTabs
A platform that lets AI agents make authenticated API calls across 100+ web services (Slack, Discord, GitHub, Jira, Notion, Figma, AWS, Stripe, etc.) through your browser session.
browser-use-mcp-server
An MCP server that gives AI agents the ability to control and interact with web browsers using browser-use automation framework.
Browser MCP
An MCP server and Chrome extension that enables AI applications to automate browser tasks while preserving login state and avoiding bot detection.
Firefox DevTools MCP
Automate Firefox browser interactions for AI agents using WebDriver BiDi protocol, with tools for page navigation, element interaction, network capture, and screenshots.
chrome-devtools-axi
A CLI wrapper for headless Chrome DevTools that optimizes browser automation for AI agents with TOON-encoded output and contextual next-step suggestions.
Safari MCP
Safari MCP is an MCP server providing 80 tools to automate Safari on macOS — your real logged-in browser, zero Chrome, ~60% less CPU.
Playwright MCP Server
MCP server providing browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, scrape content, and execute JavaScript.
Refine by platform
Refine by role
Add a skill
Know one that fits here? Submit a link — we’ll index, score, and publish it.
Add a skillRequest a skill for Browser and computer automation
Tell us what’s missing. We cluster your request with similar asks so developers can build what users actually want.
Request a skill