984 published MCP servers in this category · page 1 of 17 · all categories
Browser automation MCP integrations expose supported browser operations to an assistant. Use this category for rendered-page inspection, interface testing and browser workflows that require an interactive session.
Write down the URL, starting account state and the expected result. Test navigation, a small interaction and a screenshot before running a long sequence. Check whether the server uses a local browser, a hosted browser or an existing session; that choice determines where cookies and downloads are available.
Compare the final page with the expected behavior. A successful click does not establish that a form saved, a download completed or a test passed. Use the visible confirmation and the server documentation to decide what the workflow actually finished.
Compare vendor-maintained integrations, inspect hosted servers or return to all MCP categories.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Enables AI-powered applications to monitor and interact with browser data via a Chrome extension and MCP.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.
Integrates security testing and penetration testing tools into AI workflows via the Model Context Protocol.
Enables AI agents and LLMs to interact with the web and extract information from web pages via the RAG Web Browser Actor.
Enables enhanced web research capabilities for large language models through intelligent search queuing and advanced content extraction.
Connects MCP clients with a browser using browser-use, leveraging the client's existing LLM setup without requiring an external API key.
Automates LinkedIn interactions and extracts data through browser automation, respecting terms of service and rate limits.
Automates browser interactions and enables Large Language Models (LLMs) to interact with web pages through Playwright and Chrome DevTools Protocol
Enables agent frameworks like Model Context Protocol (MCP) to integrate with Maton APIs through function calling.
Enables LLMs like Claude to interact with and automate web browsers via the Model Context Protocol.
Enables Claude to perform Google searches and extract webpage content through a controlled Chrome browser instance.
Automates browser interactions using Python scripts for tasks like screenshot capture, HTML retrieval, JavaScript execution, and console log
Enables LLMs to interact with web pages by providing browser automation capabilities, including screenshot capture and JavaScript execution.
Captures browser console logs and provides them to Cursor IDE through the Model Context Protocol.
Exposes Bruno API collections as Model Context Protocol (MCP) tools for AI agents and other MCP clients.
Enables LLMs to control web browsers through a standardized JSON-RPC interface for automation and analysis.
Empowers AI applications to interact with and analyze data from web browsers through a Chrome extension and Model Context Protocol.
Automates browser interactions for LLMs using Puppeteer and the Model Context Protocol.
Captures screenshots of webpages using Safari on macOS.
Captures screenshots and facilitates their use by other processes or AI assistants, primarily by saving to a client-specified file path.
[!IMPORTANT] The official 2Captcha MCP package is @2captcha/mcp (published under the @2captcha npm organization). The unscoped 2captcha-mcp package on npm is not affiliated with 2Captcha — don't put…
A Model Context Protocol server
3DLogo.io, a browser 3D logo maker: 3D logos, 3D coins, 3D models from photos or prompts, embeds.
Inspect, compare and export point clouds, meshes and calibrated depth data with inline 3D previews.
Building a daily briefing for a human is mostly about sourcing the parts you can't write personally — the joke, the history snippet, the puzzle, the
MCP server for 4o-image API integration - Generate images using text prompts and edit existing images
Real-browser WCAG audit that also finds keyboard-inoperable controls axe-core misses, with fixes.
WCAG 2.2 AA accessibility checks for pages and HTML, run locally in headless Chrome.
Objective-driven deep research: free daily quick search plus MPP-paid cross-source browser reports.
Ableton Live MCP integration — fork of ahujasid/ableton-mcp adding a 33-personality style system, ~35 extra MCP tools, batch commands, and
# AccesibilityHub MCP Server for orchestrating web accessibility tools (axe-core, Pa11y, Lighthouse). Analyze web pages, check color contrast, get
Ackee analytics: domains, facts, browsers.
Autonomous web crawler. 17 browser tools + goal-driven run_goal agent. Single binary, stealth.
Security-first, read-only-by-default MCP server for ActivityPub and the Fediverse.
MCP server for the Google AdMob API — apps, ad units, mediation, and revenue reports
WCAG 2.1 AA accessibility scanner (Playwright + axe-core) with grounded, browser-verified fixes.
An MCP server that lets an AI agent drive a real browser through residential proxies, choosing the exit country / city, tier, and a sticky per-task session — at call time. The browser (Playwright…
Browser automation CLI for AI agents
MCP server for browser automation via Vercel's agent-browser CLI
Agent to integrate Playwright with ReportPortal.
MCP server that lets Claude Code agents delegate tasks to agents in other project directories
Self-hosted Chrome for AI agents, with a live noVNC view a human can take over.
MCP-compliant agentic control framework with 80+ tools for Claude Code and autonomous agent development
Give AI agents real phone numbers, messages, and voice calls via MCP.
Give your AI agent a wallet on AgentsCoin: create wallet, mine AGENT, check balance, send.
MCP server for the @agentutility browser-workflow cluster — pay-per-call x402 tools, no API keys…
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
This repo is your public entry point for Brivvy AI integrations. You get MCP server metadata, install steps, client connection profiles, and release
MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than
MCP server for AI Diagram Maker — generate software engineering diagrams from text, JSON, ASCII art, or images
Start with foura_auto: one URL in, typed content out. It chooses the appropriate fetch method and handles common blocks for you. Use foura_single, foura_proxy, or foura_browser when you want…
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
AI-powered browser automation MCP — 6 tools for web interaction, extraction, and validation.
Browser-based QA for AI-built software. Test pages with real browsers via agents.