The web
Browser automation: tools for AI agents
Drive a real browser: click, type, fill forms and take screenshots. The best matches among the MCP servers, command-line tools, web APIs and Claude Code plugins AptLynx checks every night, working ones first.
MCP servers
- BrowserHere Verified publisher · Needs a sign-in or key
Control a real browser from AI agents: navigate, click, type, screenshot, read the page. - Unstuckapi Unstuck: screenshot Verified publisher · Working at last check
Take a screenshot of a website. Open any web page URL in a real browser and capture it as a PNG image, either the visible area or the full page. Use it to see… - Wingmanprotocol Gateway: browse_open Verified publisher · Working at last check
Open a PERSISTENT browser session (cookies/login survive across calls) and get a browser_id to drive with browse_navigate/snapshot/click/type/fill/.../close.… - OfficialSpicrawl: spicrawl_scrape Working at last check
Retrieve a web page and return its content as markdown (default), text, HTML, a JSON envelope, or a printed PDF. Handles the fetch vs. browser decision,… - Zenrows: browser_screenshot Verified publisher · Working at last check
Take a screenshot of the current page or a specific element. Use for visual verification or when the accessibility tree is not sufficient. - Scraper Crawler: web_scrape Verified publisher · Working at last check
Processes a page and returns every output you ask for at once: markdown, html, links, screenshot, PDF, accessibility tree, elements by selector, AI-structured… - Skyvern Verified publisher · Needs a sign-in or key
AI-powered browser automation — navigate, click, fill forms, and extract data from any website. - shotkit Verified publisher · Needs a sign-in or key
Screenshot any URL, HTML or Markdown in a real browser, and read web pages as Markdown. - Oxylabs: ai_browser_agent Verified publisher · Working at last check
Run the browser agent and return the data in the specified format. This tool is useful if you need navigate around the website and do some actions. It allows… - io.github.AlexKay28/clickcast Runs on your computer
Drive a real Playwright browser: annotated screenshot + structured page state after every action. - Browser Automation Runs on your computer
Browser automation MCP server: navigate, fill forms, click, screenshot, and manage tabs - Hydrafetch Web: screenshot Verified publisher · Working at last check
Render a page in a real browser and capture a PNG, returning its public URL. Use when the question is what the page looks like rather than what it says. - Computer Use Runs on your computer
Control your computer with screenshots, mouse, and keyboard automation. - Validoria: create_journey Verified publisher · Working at last check
Create a custom browser test flow for a target. Steps are executed sequentially in a Playwright browser. Supports actions: navigate, click, type, fill,… - BRYG Runs on your computer
Drives a real Chromium browser: navigate, click, type, read pages, OCR, QR, network capture
Command-line tools
- playwright-cli
CLI for Playwright: record/generate code, inspect selectors, take screenshots - captura
Capture Screen, Audio, Cursor, Mouse Clicks and Keystrokes. - termshot
Creates screenshots based on terminal command output - screen-saver-control
Activate/deactivate both screen saver and monitor power off with a simple click. - cliclick
Tool for emulating mouse and keyboard events - terminal-browser
Terminal-based web browser
Web APIs
- Browshot API
Take screenshots of any website in real time tools - Urlbox API
A plugin that allows the user to capture screenshots of a web page from a URL or HTML using ChatGPT. developer_tools - Crossbrowsertesting.com Screenshot Comparisons API
What's in this version: 1. Compare two screenshots for layout differences 2. Compare a full screenshot test of browsers to a single baseline browser for… - Dataflow Kit Web Scraper
Render Javascript driven pages, while we internally manage Headless Chrome and proxies for you. - Build a custom web scraper with our Visual point-and-click… - Smartphone Test Farm
Control and manages real Smartphone devices from browser and restful apis telecom - AWS IoT 1-Click Devices Service
Describes all of the AWS IoT 1-Click device-related API operations for the service. Also provides sample requests, responses, and errors for the supported web…
Claude Code plugins
- playwright
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements,… - browser-use
Give Claude a real browser — your Chrome or a Browser Use Cloud browser. Use it whenever a task involves a website or web app: browsing, scraping and data… - webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing… - chrome-devtools-mcp
Control and inspect a live Chrome browser from your coding agent. Record performance traces, analyze network requests, check console messages with…
Search for something more specific
Related topics
Listing text is written by each tool's maker; AptLynx lists tools and does not vouch for them.