Enables browser automation through a persistent Chrome instance exposed via HTTP, including navigation, screenshots, clicks, typing, multi-tab and multi-profile management, proxy switching, login state export, and AI-driven task execution.
Enables AI agents to dynamically provision headless browser environments and connect to them through a unified HTTP/SSE MCP endpoint with persistent storage and automatic health monitoring.
Enables AI clients to drive a chosen account's isolated Chrome instance through MCP tools, covering profile discovery and start/stop, navigation, clicking, form filling, text extraction, screenshots, and queued multi-step jobs with result polling, plus manual handover for logins and CAPTCHAs. Also supports session and storage-state export, profile backups, and human takeover/resume when a task needs verification.
Enables an AI assistant to browse and interact with a real Android phone's Chrome — reading pages, navigating, clicking, typing, and running JavaScript — by reaching the browser's DevTools Protocol over an SSH tunnel relayed from the device.
Enables browser automation and inspection by connecting to an already-running Chrome/Chromium over the DevTools protocol, with page-scoped routing so multiple clients can control separate tabs concurrently.
Enables writing agents to search Bilibili videos and retrieve video information, full subtitles, and hot comments as compact plain text, using read-only access and token-efficient batch retrieval.
An MCP (Model Context Protocol) server that gives AI agents live, structured ad intelligence across Facebook, Google, and Instagram — data that no base model can produce from training alone.
Powered by Apify actors. Works with any MCP-compatible client: Cursor, Claude, etc.
Enables extracting explicitly stated contract metadata, clauses, and obligations from user-supplied contract text without storing or modifying the data.
Enables querying Shopify App Store apps and Chrome Web Store extensions by category, keyword, or listing URL, returning ratings, reviews, pricing or user counts, and developer website, domain, address, and email. Filters by minimum rating or reviews and produces one row per listing ready for outreach or enrichment.
MCP server that lets agents drive your real Chrome browser with existing logins and sessions via an outbound-only WebSocket extension. It exposes Playwright-compatible browser tools for navigation, clicking, typing, and snapshots.
Enables AI agents to drive a real Chrome browser over MCP, with each agent's tabs organized into task-named tab groups. Agents can read pages as compact outlines with element refs, then click, fill, press keys, upload files, run JavaScript, capture screenshots and inspect console/network logs.
Enables MCP clients to securely operate on browser tabs shared through OpenClaw's Chrome extension, with ACL checks enforced on every action and no raw CDP passthrough.
A headless browser MCP server that allows AI agents to fetch web content and perform Google searches without API keys, supporting various output formats like Markdown, JSON, HTML, and text.
MCP server that wraps sendblue-browser-use's HTTP API, providing tools to control a stealth-patched Chromium browser with persistent sessions, navigation, screenshots, and script execution.
Read-only observation of a single live URL: parses static HTML to report security posture, forms, links, accessibility signals, and leaks, with described fixes. SSRF-gated and safe, never executes JavaScript.
Enables governed browser automation for AI agents with human-in-the-loop approval, audit logging, and read-only replay, supporting both ASK and AUTO autonomy modes.
Provides AI agents with anti-detection browser automation through REST and MCP interfaces, including accessibility snapshots, stable element references, session isolation, proxy/GeoIP support, and search macros.
An MCP server that connects any MCP client (like Claude or Cursor) with the browser using browser-use, allowing clients to utilize existing LLMs without requiring additional API keys.
Enables any agent to drive a dedicated Chromium instance through MCP, including opening and reading pages, taking steps, logging in via a password vault, downloading/uploading files, and replaying saved routines. It also gates sensitive actions behind approvals and can use client certificates or one-time card data for official procedures.
Enables AI agents to operate a real, anti-bot-aware browser through Zyte API for navigating pages, clicking, typing, scrolling, taking screenshots, searching, and extracting structured data, with automatic proxy rotation and ban avoidance.
Enables an AI agent on a VPS to remotely control a laptop's Chrome browser through a companion extension, managing tabs, navigating pages, and interacting with website content via MCP tools.
Provides real-time Dutch railway (NS) travel information including train schedules, delays, journey planning, ticket prices, and station details for navigating the Netherlands by train.
Enables AI assistants to capture screenshots of web pages using automated browser sessions. Supports full-page and element-specific screenshots, device simulation, and JavaScript execution for comprehensive web testing and monitoring.
This MCP server provides tools for interacting with Cloudflare Browser Rendering, allowing you to fetch and process web content for use as context in LLMs directly from Cline or Claude Desktop.
An MCP server that uses Puppeteer and headless Chrome to scrape YouTube transcripts directly from the video page UI. It provides tools for fetching plain text transcripts, timed segments with deep links, and video metadata while bypassing standard API rate limits.
Enables users to audit personal reading streams by quantifying category diversity with Shannon entropy, detecting lexical redundancy and echo chambers via Jaccard similarity, and ranking content sources by decibel signal-to-noise ratio for pruning recommendations.
Enables AI agents to drive their own sandboxed Chromium containers over MCP — navigating, reading pages, clicking, filling forms and signing in — while each profile keeps persistent cookies, is restricted to an allowlisted set of domains, and keeps stored passwords out of the agent's context. Operators manage profiles, leases, live browser viewing and human handoffs from a local admin UI.
Enables offline browser compatibility and Baseline status lookup for web features, including support checks, search, and comparison against browserslist targets, using bundled MDN, web-features, and caniuse data.
Provides reusable authenticated Chromium identities and one shared-control Session Browser per DSH session, enabling an agent to drive the browser through Playwright MCP while a user operates it via noVNC.
Enables browser-based AI services to connect through remote MCP for internal document search, email checking and replies, timecard, sales/project, schedule/task, and operations tasks. It supports multiple AI clients via compatible remote MCP endpoints.
Enables AI agents to drive a self-hosted Chromium through MCP tools for opening pages, reading content, taking screenshots, clicking, filling forms, and triggering final submissions, while a human watches the same browser live and can take over for logins or captchas. Server-side guardrails enforce per-session domain allowlists and denylists, refuse password, payment card, IBAN and one-time-code fields, isolate each token in its own browser context, and route submits, payments and orders through a separate final-action tool that can require human approval.
This MCP server enables users to analyze personal reading and media streams by computing Shannon entropy, detecting Jaccard redundancy and echo chambers, and ranking content sources by decibel SNR to produce pruning recommendations and high-signal curation.
Provides access to Canadian federal parliamentary data (debates, bills, MPs, votes, Hansard transcripts) and legal information (case law and legislation through CanLII) for research and analysis.
Enables a single user to let ChatGPT read and control a dedicated Chromium browser running on their own server, with tab, navigation, and browser-action tools plus manual approval safeguards.
MCP server for remotely controlling BitBrowser antidetect profiles via Playwright with built-in behavioral stealth, enabling automated browser tasks with anti-detection capabilities.
Enables MCP clients to automate a real browser by stating one outcome at a time, with a decision model picking the element, action, value, and done/blocked/error status while Playwright executes. Also exposes page reading, snapshots, screenshots, direct element actions, and calling a page's own WebMCP tools.
Provides stealthy browser automation capabilities using a custom Firefox build designed for anti-detection. It enables users to navigate pages, interact with elements, and manage persistent browser sessions through natural language.
Enables AI agents to drive a remote headless Chromium browser through Playwright on Vercel serverless functions, supporting navigation, snapshots, clicking, form filling, key presses, scrolling, text extraction, screenshots, and JavaScript evaluation. Browser state is carried in an encrypted client-side session token, so no database or third-party browser service is required.
A browser automation MCP server hosted on Vercel that enables AI agents to perform web interactions like clicking, typing, and capturing screenshots via Browserless.io. It supports persistent session management and Basic authentication for seamless navigation across protected sites.
Retrieves comprehensive patient information including personal details, insurance plans, and employee data through the get_patient tool. Supports Docker Compose deployment and integration with Watson Orchestrate for healthcare data access.
Enables remote browser automation via MCP, allowing models to open pages, read snapshots, click, fill, and select elements using Playwright, with built-in security restrictions against sensitive actions.
An MCP server that gives AI clients controlled access to a real headless browser with domain allowlisting, SSRF protection, per-session isolation, audit logging, and persistent cookies/state across restarts.
Lets an MCP client read allowlisted pages from the LiveSwapFace website, retrieve its official links, and estimate credits for a planned browser session using rates fetched at call time. It is read-only and never performs face swaps, signs in, uploads media, or touches a private API.