Browser Automation MCP servers

MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR

Automate a real, logged-in browser on your own device — no stored credentials, no bot detection.

Self-hosted MCP server: sandboxed browser, desktop, vision, code-edit packs for any agent.

Drive Android & iOS mobile-app automation from your AI agent on locally connected devices.

Drive a running Ikenga desktop app from MCP clients — DOM, click, type, navigate, screenshot.

Local MCP server for desktop automation: mouse, keyboard, screen, windows, and processes.

Stealth Chromium MCP server with hybrid AOM + Set-of-Mark vision and Readability extraction.

macOS desktop control for Claude: click, type, screenshot, AX tree, browser control, agentic loops.

Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction.

AI-native browser runtime for autonomous agents with human-in-the-loop supervision

Browser automation MCP for solving captchas with CapMonster Cloud via Patchright.

macOS computer use with the guardrails on: passwords blacked out, writes need consent, all logged.

MCP server for Chrome DevTools

MCP server for Chrome DevTools

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

Browserbase MCP server: cloud browser sessions, agents, contexts, fetch, search, functions

Capture web pages as screenshots (returned inline) or PDFs via the Screenshotty API.

Complete web tasks in the user's own Chrome via an observe-decide-act browser agent.

AI browser automation. Write async Python to navigate, click, type, and extract data.

Control a local headless Chrome browser: open pages, read titles, and take screenshots.

Point at visible targets in an agent-built interface, and deliver grounded Annotations.

Windows desktop automation that re-reads only what changed: 7x fewer tokens per task.

Motion sensor for AI agents: tells when a screen region changes or goes still. Scores, never pixels.

Your AI sees the screen but can't measure it — measured web UI findings, shared live sessions

USB-HID keyboard/mouse (Pico 2, open firmware) as MCP tools; --mock runs with no hardware

Drive a real Playwright browser: annotated screenshot + structured page state after every action.

Windows MCP server replicating Anthropic's computer-use tool surface, for any MCP client.

macOS automation: 17 typed tools for windows, menus, keyboard, clipboard, tabs, screenshots