Loading...
The definitive directory of Model Context Protocol servers. Connect your AI assistant to GitHub, databases, file systems, APIs, and hundreds of other tools.
The Model Context Protocol (MCP) is an open standard that enables AI assistants like Claude, Cursor, and ChatGPT to securely connect to external data sources and tools. MCP servers act as bridges, allowing your AI to read files, query databases, call APIs, and take actions on your behalf.
MCP servers run locally, keeping your data private and secure
One integration works with Claude, Cursor, ChatGPT, and more
Build custom MCP servers for your specific needs and workflows
MCP servers enable AI assistants to connect to external systems like GitHub, PostgreSQL, Slack, Google Drive, file systems, and custom APIs. They allow your AI to read, write, and take actions on your behalf.
Installation varies by client. For Claude Desktop, you add server configurations to your claude_desktop_config.json file. For Cursor, you configure them in settings. Each server listing includes installation instructions.
Most MCP servers are open source and free to use. Some may require paid API access to the underlying service they connect to (e.g., a database or SaaS tool).
MCP servers run locally on your machine, giving you full control over what data your AI assistant can access. You decide which servers to install and what permissions they have.