460 reviewed MCP servers in this category · page 5 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.
A Model Context Protocol (MCP) server for controlling QEMU virtual machines via SSH. This server enables LLMs to interact with VMs through
1. **Performance Optimization** - Match speed of Ubuntu desktop alternatives 2. **Apple Scripts Generation** - Reduce execution time while
1. **Open your browser** to `http://localhost:8501` 2. **Get a free API key** from [OpenRouter.ai](https://openrouter.ai) 3. **Add your API key** in
A Model Context Protocol (MCP) server that provides advanced HTTP request capabilities for Claude and other LLMs. Built on
MCP server for browser automation using Puppeteer
A Model Context Protocol server that provides screenshot and OCR capabilities
Fast screenshot capture tool for web pages - optimized for Claude Vision API
Telegram MCP server (MTProto). Connect Claude, Cursor, Claude Code, VS Code, Codex, Cline, Windsurf to a real Telegram account — read/search/send
A **Model Context Protocol** server that lets Claude Desktop / Cursor / any MCP client drive your test suite end-to-end: run tests, inspect failures
The `voicevox_speak_player` tool uses [MCP Apps](https://github.com/modelcontextprotocol/ext-apps) to render an interactive audio player directly
A [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that enables AI agents (Claude Code, Cursor, Windsurf, OpenCode) to launch
An MCP service built on undetected-chromedriver, providing a comprehensive interface for automating Chrome browser control while bypassing anti-bot
<h2 align="center">built with</h2> <picture> <source media="(prefers-color-scheme: dark)" srcset="static/logo_white.svg"> <source
A universal CLI and MCP server tool for fetching, extracting, and processing web and API content. Supports resource blocking, authentication, Google
MCP server for web research
MCP server for web research
A self-hosted SearXNG metasearch engine paired with the `mcp-searxng` MCP server, **built for LLMs, agents, and tool-using applications**. Lets your
A Model Context Protocol (MCP) server that provides comprehensive website snapshot capabilities using [Playwright](https://playwright.dev). This
MCP server for WeGene Assistant, using LLM to analyze a user's WeGene genetic testing report.
A MCP server for capturing screenshots on Windows
Simple MCP Starter Package
Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.
The Meilisearch JS client for Node.js and the browser.
Mercury Parser transforms web pages into clean text. Publishers and programmers use it to make the web make sense, and readers use it to read any web
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images
Generat 22 types mermaid architecture diagrams with natural language description
MCP server for generating [Mermaid](https://mermaid.js.org/) diagrams with live browser preview. Renders diagrams in real-time and supports SVG/PNG
Brazilian tools for agents: Pix codes, CEP, CNPJ + web capture and PDF. Pay per call.
Control a real iPhone through macOS iPhone Mirroring: screenshot, tap, swipe, type.
MCP server that gives AI coding assistants (Claude, Cursor, Windsurf) the ability to see and interact with Android mobile devices via ADB —
This runs against your modal account, so you will need to have a modal account and be logged in.
Modular MCP - Modular tool access for reducing context overhead
The configuration file will be generated at `/Users/username/.moling/config/config.json`, and you can modify its contents as needed.
Hallucination-proof scroll motion: LLM writes validated specs, deterministic GSAP/CSS compiler.
E2E test runner using Chrome Pool (browserless/chrome) with parallel execution
A versatile MCP-compliant web content fetching tool that supports multiple modes (browser/node), formats (HTML/JSON/Markdown/Text), and intelligent
Bug translation for vibe coders: plain-English diagnosis + paste-ready fix in your AI coding agent
このリポジトリは、複数の MCP (Model Context Protocol) サーバーを管理し、Docker Compose を使用して簡単に起動するためのプロジェクトです。 各 MCP サーバーはサブモジュールとして管理されており、それぞれ特定の機能を提供します。
AI-powered localization — translate, manage translation memory, and access style guides.
Next.js development tools MCP server with stdio transport
Yet another WebUI for Nginx
Screenshot API for MCP clients. Capture any URL as PNG with mockup mode support.
Crypto tools for Node-OPCUA
Control browser sessions, AI agents, and web scraping through intuitive <strong>resource-based commands</strong>
[screenshot: Novada connected in an MCP client, tool list visible]
A Model Context Protocol (MCP) server implementation that integrates with the Nutrient Document Web Service (DWS) Processor API, providing powerful
CLI and MCP server for NAVER WORKS / LINE WORKS — control messages, calendar, drive, mail, tasks, and boards from terminal or AI agents (Claude
MCP server adapter for Obscura Rust headless browser — web scraping with anti-detection.
Drive OctoPerf load testing from any AI agent: import, edit, validate, run scenarios, read metrics.
🚀 OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.
Browser extension for annotating UI elements for AI agents
Model-agnostic computer-use MCP: screenshot, safety-gated actions, Windows UIA targeting.
Load OpenAPI 2.x/3.x specs and expose generic tools to discover and call multiple APIs
Open Browser Use Chrome extension, native host, and SDK workspace.
Unofficial MCP server connecting OpenEvidence to AI agents via authenticated browser sessions
Stdio MCP bridge for the hosted OpenRegistry service
Turns tabs into tools
MCP server for OriginUI components with search and installation capabilities
Outlit gives agents real-time understanding of customers to automate support and revenue workflows.
MCP server for PageBolt — take screenshots, generate PDFs, create OG images, inspect pages, record demo videos with Audio Guide narration, from AI