Smithery is now a part of Arcade.dev! Read more in our announcement here
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to interact with web pages, take screenshots, and run parallel sessions in a cloud browser environment.
Web scraping and automation platform. Run scrapers, extract structured data, and automate browser-based workflows.
WebRun gives AI agents a real Chrome browser running in the cloud. Instead of wiring up an API for every service, your agent does the work the way a person would: it opens the site, signs in, clicks through the flow, and reports back. Sessions run on persistent environments that keep their Chrome profile, cookies, files, and desktop state, so an agent stays logged in across runs instead of re-authenticating every time. Every session streams live, and a human can take control mid-task to clear a CAPTCHA or enter a credential, then hand it back.
Give your AI a real computer and let it finish the job. Noxgild gives agents secure access to authorized Windows, macOS, and Linux computers plus a hosted Cloud Browser, so they can actually complete work end to end: write and modify files, run commands, manage long-running processes, use signed-in websites, operate native apps, test software, investigate issues, deploy changes, and execute multi-step workflows. Keep using the AI tools you already know while Noxgild provides the execution layer—with approvals, credentials, and protected human gates remaining under your control.
Hosted Playwright browser automation for AI agents. Returns accessibility trees instead of screenshots, cutting token usage by 77%. Navigate, interact, extract structured data, and take screenshots — all via MCP. Zero infrastructure, credit-based pricing.
Enable AI assistants and applications to perform automated web browser interactions, testing, and scraping through a standardized interface. Control multiple browsers with comprehensive element interaction and advanced navigation tools. Benefit from type-safe, robust browser automation powered by Selenium WebDriver.
Reduck MCP allows agents to discover, run and create browser automation scripts that serve as tools. Scripts run in your own Chrome, through our extension, which allows your agent to work where you are logged in — no credentials exposure, and same fingerprints so no bot detection.
Scrape any page or document to markdown, map and crawl whole sites, and drive a real browser — all from one server. Pay per call with a wallet. No API key, no signup, no monthly plan. Keyless clients get a free daily allowance so the first call works before any account exists. What it does that a scraper usually does not A map of the controls — every link, button and field with its role, its readable name and where it sits on screen. The map an agent needs to decide what to click. Browser sessions that stay open — look, click, look again, without reloading and without losing state. Documents by url — PDF, Word, Excel and CSV come back as markdown, no browser involved. Every output in one call — markdown, html, links, controls, accessibility tree, elements by selector, screenshot, PDF, or AI-extracted JSON. Tools: webscrape · webmap · webcrawl · websessionopen · webact · webscrapebatch · websearchexa · and status, c
Give your AI agent the live web. One MCP server for Search, Fetch, Browser, and Agent: browse real sites, extract structured data, fill forms, and run multi-step workflows. Search and Fetch are free.
Deploy and manage Kernel apps, automate browsers, and search documentation with Kernel. Securely run workflows, monitor deployments, and spin up sandboxed browser sessions, all instantly accessible through a hosted service built for AI-native automation.
Scrayle.com gives AI agents full web access through 35 tools spanning scraping, browser automation, AI-powered browsing, workflow orchestration, and more. • Scrape & Crawl - Extract content from single pages or crawl entire sites. Batch scrape multiple URLs at once. Get clean markdown, HTML, links, and metadata. • Cloud Browsers - Launch stealth cloud browsers with anti-detection. Navigate, click, type, screenshot, scroll, select dropdowns, and execute JavaScript - all remotely. • AI Browser Agent - Let an AI agent browse the web autonomously. Give it a task and it figures out the clicks, scrolls, and form fills on its own. • Workflows Create, run, and manage multi-step automation workflows. Chain scraping, browser actions, and data processing together. • CAPTCHA Solving Solve reCAPTCHA, hCaptcha, Turnstile, and other challenges automatically. • Marketplace - Browse and run pre-built scraping templates from the Scrayle marketplace. • Key-Value Storage - Store and retrieve data
Headless browser via Playwright. Scrapes JS-rendered pages, takes screenshots, extracts links and tables, fills forms, runs arbitrary JS. Useful when fetch() is not enough.
Browser automation for AI agents that returns the answer, not a screenshot: live prices, stock and availability, search results, quotes, fares, bookings, and data behind a form or a login. An MCP server that runs the real task on the real website and extracts structured data from the live page, with no browser to drive. Search a site, price a product, drive a configurator, start a booking. Covers flights, hotels, car hire, PC parts and insurance across sites including Kayak, Google Flights, Newegg, Micro Center, B&H Photo, Marriott and Hilton. Call get_library for the typed function library, then run a short JavaScript script written against it. Free Bowmark account with $10 of usage a month.
Any website as MCP tools: Unbrowse replays a site's own first-party API server-side and returns verified results — no browser on your side. Search thousands of indexed sites, run their tools, read pages, sign in from your saved logins, and learn new sites in a recorded cloud browser.
Turns any webpage into a structured action manifest — a list of what's clickable, fillable, and submittable, not just what's on the page. Built for agents that need to act on a page, not just read it.
Agent-first browser server: one Rust binary with V8 built in. Tiered fetch, multi-engine search, screenshots, downloads, click/eval, persistent login sessions, and render_markdown (markdown + archify diagram fences to deterministic HTML+SVG artifacts). Stealth TLS fingerprints, optional 2captcha integration, no Chromium.
Zero-configuration on-demand cloud browser for your agent. Navigate web pages, fill forms, and capture screenshots effortlessly with pay-as-you-go pricing at just $0.10 per hour. Exposes Chrome Devtools MCP interface.
Token-efficient web browser for LLM agents
Use your Mac, Windows (beta) or Linux computer from ChatGPT, Claude and other AI apps: read and organize files, edit Excel and PDFs, run commands, and on a Mac edit videos and build iOS apps. Computers start read-only; you turn on each permission per computer.
Screen Browser records narrated demo and tutorial videos of your deployed web app. You describe the walkthrough in plain language, or let your coding agent write it from your source code. A real browser signs in with a demo account, follows the guide step by step, records the screen, narrates it and adds on-screen effects. You get an MP4 plus a GIF, subtitles, chapters and a thumbnail, and a webhook or the API can deliver them wherever you publish. When the app changes, edit a line and rerun. For coding agents, Screen Browser is an MCP server with a companion skill. The skill teaches the agent how to write guides that work on the first run; the server creates the project, validates the guide, starts the recording and returns the video. Claude Code, Codex, Cursor or any MCP client can use it. Sign-in happens in the browser; there is no key to paste. What it needs: a web app reachable over the internet, and a demo user that signs in with email and password (no OAuth, no two-factor
Fetch any public web page through managed proxies, with optional JavaScript rendering, wait conditions and CSS or AI extraction rules, as markdown, text, HTML or JSON. Runs on HasData's hosted API.
