MCP Servers

The open registry for Model Context Protocol servers. Find the right tools, resources, and prompts for your AI agents — filtered by category, transport, or use case.

Servers

175

Tools

465

Categories

11

Contributors

153

CategoryAll34Database26Development25Productivity24DevOps17Research13Cloud11Communication9AI6Browser Automation6Security4Filesystem
TransportAllstdioSSEHTTP Streaming

4 servers

Sort by
Directus MCP ServerDirectus

Directus' MCP integration connects agents to headless CMS data, schemas, and operations for governed content and application workflows.

0 ★
Playwright MCP ServerMicrosoft

Microsoft's official Playwright MCP server that provides browser automation capabilities for AI agents. Enables navigating web pages, clicking elements, filling forms, taking screenshots, and extracting content. Supports headless and headed modes with Chromium, Firefox, and WebKit browsers. Ideal for web testing, scraping, and interactive browsing tasks.

33k ★
Browserbase MCP ServerBrowserbase

Official Browserbase MCP server for cloud browser automation. Lets AI agents create headless browser sessions, navigate pages, extract content, take screenshots, and perform actions using Stagehand, enabling reliable web automation and scraping at scale from AI-powered tools.

1.1k ★
Contentful MCP ServerContentful

Contentful's official MCP server for the Content Management API. Gives AI agents tools to create, edit, organize, and publish content, manage content models and assets, and work across spaces and environments. Useful for automating editorial workflows and content operations in a Contentful-backed headless CMS.

0 ★

Skills vs MCP servers

what’s the difference?

Skillsthe “what to do”

A skill packages know-how — instructions, an example prompt, and recommended models — so an agent performs a task consistently. Skills add knowledge, not new connections.

MCP serversthe “how to connect”

An MCP server gives an agent new capabilities by connecting it to real systems (databases, APIs, files) over a transport. MCP adds connections and actions, not task instructions.

Rule of thumb: reach for a skill when you need the model to do a task well, and an MCP server when you need it to reach a tool or system. They compose — a skill can rely on tools an MCP server provides.

Built an MCP server?

Submit it to the registry — it’s open source and community-maintained.

Submit on GitHub