MCP Servers
63,071 MCP servers for AI apps. Filter by category, badge and popularity.
Browser Automation
MCP Agents is an AI-powered browser automation tool that lets you interact with websites using natural language. Built with Streamlit, OpenAI, and Puppeteer via the Model Context Protocol (MCP), it supports multi-step navigation, interaction, and content extraction—all with simpl
Cloud-native solution for LLMs and AI agents with fingerprint-isolated browser environments and automation APIs. No local deployment needed; eliminates performance bottlenecks and operational overhead so developers can focus on core logic. Features include fingerprint-isolated cloud environments with independent isolation across instances, supporting untraced automation; browser behavior simulation with precise web access, element-level screenshots, dynamic data extraction, and intelligent form filling; LLM-optimized adaptation with browser behavior trajectory simulation, DOM tree parsing optimization, and structured data output; elastic resource scheduling from single-session debugging to thousands of concurrent operations with automatic compute matching.
An MCP (Model Context Protocol) server that fetches and summarizes Wikipedia articles using Ollama LLMs, accessible via both command-line and Streamlit interfaces. Perfect for quickly extracting key information from Wikipedia without reading entire articles
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.
