Search MCP servers
Filter by capability, transport, auth, language, and verification.
24 results
Microsoft's official browser-automation MCP using Playwright's accessibility tree (no vision model).
Control Blender from Claude and other LLMs for prompt-assisted 3D modeling, scene creation, and asset generation.
macOS screen capture, AI visual analysis, and full GUI automation for AI agents.
Popular community Playwright + API testing MCP server with codegen, screenshots, and device emulation.
Connect Claude, Cursor & Windsurf to the Unity Engine for AI-driven game development in Editor and Runtime.
Official Browserbase cloud-browser MCP built on Stagehand — natural-language act/extract/observe.
Control and inspect iOS simulators — UI taps, swipes, text input, screenshots, video, and app install/launch.
Computer-use MCP server that automates Windows desktop and browser apps via the accessibility tree.
Autonomous browser agent that evaluates and debugs your web app end-to-end from your IDE.
Free, no-rate-limit Figma MCP server with full read/write via a plugin bridge — no REST API token needed.
Control Android devices from MCP clients via ADB — run shell commands, capture screenshots, inspect UI, manage packages.
Comprehensive Xcode integration for AI assistants: projects, builds, tests, simulators, SPM and CocoaPods.
Drive AutoCAD LT via AutoLISP or generate DXF headlessly — 8 consolidated tools for drafting, P&ID and screenshots.
Control iOS simulators with natural-language commands from your LLM, powered by Facebook's idb.
Browser automation via Playwright — let LLMs navigate, click, fill forms, screenshot, and run JS in a real browser.
Automate and inspect Firefox via WebDriver BiDi (Selenium) from any MCP client.
MCP server exposing Playwright browser-automation tools: navigate, click, fill, screenshot and scrape pages.
Native Safari browser automation for AI agents on macOS — 80 tools, your real logged-in browser, no Chrome.
Autonomous browser automation for Claude Desktop via Playwright, plus an HTTP API client.
Persistent code index + memory, semantic search & live telemetry for AI coding agents — 50x less context than grep.
Community server that captures website screenshots via the ScreenshotOne API.
Render screenshots of any website and return them as images, via the ScreenshotOne API.
Drive Chrome, Firefox, Edge, Safari and iOS/Android apps with WebDriverIO, locally or on cloud devices.
Scrape websites, search engines, eCommerce, and social media for AI agents via Decodo's Web Scraping API.