# What is the MCP Registry?

The MCP Registry is the official, central repository of metadata about publicly available MCP servers: each server's verified name, description, version and where to get it, stored in a server.json format. It points to code hosted elsewhere and is read mainly by directories and marketplaces.

## What it does and doesn't do

- **Verifies names.** Server names are reverse-DNS style (`io.github.user/server`, `com.example/server`), and only the owner of that GitHub account or domain can publish under them.
- **Stores metadata, not code.** Packages stay on npm, PyPI, Docker Hub and similar registries.
- **Leaves security scanning to others.** Its docs delegate scanning to package registries and downstream directories.
- **Public servers only.** Private servers belong in your own registry.

As of 19 November 2026 the registry is in preview, and its docs warn of possible breaking changes or data resets before general availability. This directory discovers new servers from it. To list your own server, see [publish to the MCP Registry](https://ai-powered.com/academy/build-mcp-servers/publish-to-mcp-registry).

## Sources

Official documentation, checked on 19 November 2026:

- [The MCP Registry (modelcontextprotocol.io)](https://modelcontextprotocol.io/registry/about)

## Related terms

- [MCP](https://ai-powered.com/academy/glossary/mcp): MCP (Model Context Protocol) is an open standard for connecting AI applications to outside tools and data. An AI app connects to small programs called MCP servers, asks each one what it offers, and calls those tools when a task needs them.
- [Remote vs local MCP server](https://ai-powered.com/academy/glossary/remote-vs-local-mcp-server): A local MCP server is a program the AI app starts on your own computer and talks to over standard input and output (stdio). A remote MCP server runs on someone else's machine and the app reaches it over the internet by URL, using Streamable HTTP and usually a sign-in.
