MCP Servers
63,071 MCP servers for AI apps. Filter by category, badge and popularity.
Browser Automation
Your AI agent scrapes X today, gets broken HTML tomorrow. Taprun compiles the site once into a deterministic program, then `tap doctor` monitors health contracts + structural diffs to catch silent breakage before your data goes stale. 140+ pre-built skills across 68+ sites. Works
This is an experimental project to integrate Playwright with MCP. The plan is to conduct in-depth research, understand the intricacies of the integration, and review the best articles on the web to create the optimal version of a project using both technologies.
Stop feeding your agent raw HTML. BrowserControl gives LLMs true visual grounding with Set of Marks (SoM), letting them click exactly what they see without hallucinating selectors. With built-in developer tools, session recording, and persistent logins, it transforms web automation
This project demonstrates how to use Cloudflare Browser Rendering to extract web content for LLM context. It includes experiments with the REST API and Workers Binding API, as well as an MCP server implementation that can be used to provide web context to LLMs
One call turns any web page into a structured map — what it is, what's on it, and the actions an agent can take (search, add-to-cart, log in, paginate) — instead of raw HTML or screenshots. Served from a shared, always-current registry, so popular pages return in milliseconds.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
