🔌 Awesome MCP Servers

The most comprehensive, curated collection of Model Context Protocol (MCP) servers.

Unlike other lists, we focus on quality over quantity — featuring battle-tested, actively maintained servers with real-world configurations and developer-focused organization.

<p align="center"> <a href="#-quick-start">Quick Start</a> • <a href="#-official-servers">Official Servers</a> • <a href="#-by-category">By Category</a> • <a href="#-by-stack">By Stack</a> • <a href="#-configurations">Configurations</a> • <a href="#-contributing">Contributing</a> </p>

---

📖 What is MCP?

Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect with external tools, data sources, and services. Think of it as a universal plugin system for AI — allowing Claude, Cursor, VS Code Copilot, and other AI tools to interact with your development environment, databases, APIs, and more.

Why MCP Matters

Before MCP	With MCP
Copy-paste context manually	AI reads your codebase directly
Switch between tools constantly	Unified interface for everything
Limited to training data	Real-time access to live data
Generic responses	Context-aware, personalized help

---

⚡ Quick Start

1. Choose Your Client

Client	Platform	Setup Guide
Claude Desktop	macOS, Windows	Official Guide
Cursor	macOS, Windows, Linux	Cursor MCP Docs
VS Code + Continue	All platforms	Continue Extension
Windsurf	macOS, Windows, Linux	Windsurf Docs

2. Install Your First Server

# Using npx (recommended for TypeScript servers)
npx -y @modelcontextprotocol/server-filesystem /path/to/allowed/directory

# Using uvx (recommended for Python servers)
uvx mcp-server-git --repository /path/to/repo

3. Configure Your Client

Add to your client's configuration file:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/you/projects"]
    }
  }
}

📁 Ready-to-use configs: Check our configs/ directory for complete setups by use case.

---

🎖️ Official Servers

These are reference implementations maintained by Anthropic and the MCP team. Start here.

Server	Package	Description	Transport
Filesystem	@modelcontextprotocol/server-filesystem	Secure file operations with configurable access controls	stdio
Fetch	@modelcontextprotocol/server-fetch	HTTP client for web requests, returns markdown/JSON	stdio
Git	@modelcontextprotocol/server-git	Local Git repository operations and analysis	stdio
Memory	@modelcontextprotocol/server-memory	Persistent knowledge graph for cross-session context	stdio
PostgreSQL	@modelcontextprotocol/server-postgres	Read-only database access with schema inspection	stdio
SQLite	@modelcontextprotocol/server-sqlite	SQLite database operations with built-in analysis	stdio
Brave Search	@modelcontextprotocol/server-brave-search	Web search via Brave's privacy-focused API	stdio
Puppeteer	`@modelcontextprotoc