460 reviewed MCP servers in this category · page 2 of 8 · all categories
Browser automation MCP servers let an AI assistant drive a real browser: open pages, click buttons, fill forms, take screenshots and pull content out of rendered DOM. They're the backbone of agentic testing, scraping dynamic sites and automating web workflows that have no API. Most run a headless Chromium locally; a few hand the browser off to a cloud fleet so nothing runs on your machine.
<details> <summary><strong>Sister projects from n24q02m</strong> (click to expand)</summary>
MCP server that integrates with FE development server for Cursor
Real-time interest rate data: swap rates, forward curves, FX, bonds for 60+ indices.
Blueprint MCP monorepo - MCP server and browser extensions
A local, human-governed room where MCP-compatible AI agents collaborate on one codebase while you watch and stay in command. Per-agent git branches
DeepSearch MCP Server with Brave Search API and Puppeteer content extraction
Visual Desktop Bridge - Give any AI full control over Windows to automate apps and inputs.
Full-page browser screenshots, from the command line or from your own code, with the pixels, the text, and the HTML all handed back together.
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
AI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover.
Make websites accessible for AI agents
MCP server for remote browser automation using BrowserCat
An MCP server paired with a Firefox browser extension that provides AI assistants with access to tab management, browsing history, and webpage text
MCP server that gives AI coding tools the same CSS visibility you have in DevTools — rendered class names, full cascade, what's winning and why.
MCP (Model Context Protocol) server for the Browserless.io browser automation platform
A Model Context Protocol server for taking screenshots of web pages using Playwright
# MCP Browser Automation with Ollama A powerful browser automation system that enables AI agents to control web browsers through the Model Context
Co-browse with your AI as you edit code. A headed Playwright-controlled browser with accompanying MCP server.
Project management for coding agents. Bugs, features, sprints. 71 tools, stdio or remote SSE.
Publish, schedule, and manage social media across 11 platforms via MCP.
Anti-detection browser automation with Camoufox - stealth Firefox for web scraping
Let AI agents see and interact with terminal/CLI apps via PNG screenshots
Capacitor plugin for voice recording
An MCP server that searches for car deals from Cars.com, Autotrader, and KBB
No-account public website privacy risk scans with 20 new scans/day and free recent-result reuse.
BDD/TDD assertion library for node.js and the browser. Test framework agnostic.
Renders web pages into structured, agent-readable representations using headless Chromium.
Create interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON)
# ChatData MCP 服务器 ChatData MCP 服务器是一个基于 Model Control Protocol (MCP) 的服务应用程序,提供了丰富的工具集和提示系统,用于增强大型语言模型的能力。 ## 项目简介
Drive your real Chrome browser over MCP — real logins, real cookies. A stdio MCP server (CLI) plus an MV3 extension, driving Chrome via
Control a Chrome browser through the Chrome DevTools Protocol (CDP) from MCP clients for browsing, inspection, and automation workflows.
MCP Server for Chrome browser automation via debugging protocol with session persistence
This MCP allows you to record browser interactions with a chrome extension that include screenshots and console logs. The data is then saved to a
Chrome DevTools MCP Server for AI-assisted frontend development
A Model Context Protocol (MCP) server that provides browser automation capabilities using chromedp. This server enables AI assistants to interact
Chromewright is a local-first browser automation MCP server built on Chrome DevTools Protocol (CDP). It exposes a real Chrome or Chromium browser to
MCP bridge between Chromium browsers (Arc, Vivaldi, Brave) and Claude Code: browser automation
Snowfort Circuit MCP - Computer use for webapps and electron apps
MCP server for providing web context to LLMs using Cloudflare Browser Rendering
Client-Tool-Execution MCP Server
A Model Context Protocol server that provides access to the currently active tab of cmux
Structural similarity-based code filter. Stops malicious code pattern reaching execution tools.
A lightweight JavaScript MP4 (MPEG-4, ISOBMFF) file/box parser.
AI-driven JavaScript dead code elimination for Cursor (MCP server)
[](https://www.npmjs.com/package/@agentclientprotocol/codex-acp)
Easily create reusable automation tools from casual browser actions using Apify Agent
CodingBaby-Browser-MCP is a powerful tool that enables AI assistants like Claude 3.7 Sonnet in Cursor to control Chrome browser for automated tasks.
MCP server for CoinStats API integration — stdio CLI + Cloudflare Worker
MCP Server that gives Claude Code superpowers with Perplexity Comet browser - agentic web browsing, deep research, and real-time monitoring
OR install globally with `pip`: ```bash pip install computer-control-mcp ``` Then run the server with: ```bash computer-control-mcp # instead of uvx
MCP stdio server for fetching Confluence Wiki pages with managed browser authentication.
A podman ubuntu 24.04 container that serves a MCP server; with file, code execution, bash shell, knowledgebase, and more.
Easily pickle/serialize/freeze/store and re-hydrate complex JavaScript objects (including Functions)
Crystallize headless commerce tools for AI agents via Model Context Protocol
Enable AI Agents to fix Playwright test failures reported to Currents.
A production-grade **Model Context Protocol (MCP) server** that turns Claude into a full-spectrum security analyst. Instead of juggling 15+ browser
🪟 Darbot Windows MCP - Professional Windows desktop automation server for AI agents via Model Context Protocol (MCP). Control Windows like a human
A Model Context Protocol (MCP) server that provides tools to interact with the [Dash](https://kapeli.com/dash) documentation browser API.
LLMs are great at generating options and bad at telling you which one a real person will prefer. Datapoint MCP closes that loop — your agent can hand
MCP server for DebugAI. Browser sign-in, auto client setup, no key pasting.