mcp-registry
🔌 Unofficial web app to browse the official registry for Model Context Protocol (MCP) servers.
claude mcp add --transport stdio vemonet-mcp-registry npx -y mcp-registry
How to use
This MCP registry UI provides an in-browser interface to browse and install MCP servers published to the official MCP registry. You can search by server name, filter by last published date, and optionally enable client-side indexing to filter by server type and descriptions. The UI lets you view published versions, configure installation options for each server, and export your selected stack to clients like VSCode or Cursor. It fetches data directly from the registry endpoint and does all processing in the browser, so you can evaluate servers without running any backend yourself. To install a server, use the built-in one-click installation flow from the registry UI when you have a target client configured (VSCode or Cursor) and follow the prompts to generate and apply an mcp.json configuration.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- A modern browser (Chrome, Firefox, Edge, etc.)
Installation steps:
- Install dependencies for the registry UI (from the repository):
npm i
- Start the development server (for local testing):
npm run dev
- Build for production when ready:
npm run build
- If publishing a binary or container in a deployment workflow, ensure the built assets are served by your chosen hosting method (e.g., static hosting or a simple HTTP server). For quick testing of a production-like build, you can copy the dist folder to a static server and run a simple HTTP server:
cp -R dist dist/mcp-registry
npx http-server dist -o mcp-registry
- Documentation and usage hints are available in the repository's README and in-code comments for developers contributing UI features.
Additional notes
Tips and caveats:
- This UI runs in the browser and fetches data directly from the registry, so ensure the registry URL is accessible from your environment.
- No server-side installation is required to browse the registry; installation is performed by the clients (e.g., VSCode or Cursor) using the generated mcp.json configuration.
- If you plan to customize or deploy the UI, keep dependencies up to date with npm i and use npm run fmt and npm run typecheck during development.
- For production deployments, the built dist folder is production-ready; you can serve it with any static hosting solution.
- If you run into CORS or network issues fetching registry data, verify registry URL accessibility and consider hosting a local mirror or using a trusted public registry URL.
- The new-release workflow and upgrade scripts help keep dependencies current; use npm run upgrade to update to latest compatible versions.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
promptboard
The Shared Whiteboard for Your AI Agents via MCP. Paste screenshots, mark them up, and share with AI.