Plate

v1.0.0Developer Toolsstable

Rich-text editor with AI and shadcn/ui

aimcpreactshadcn-uislate
Share:
16,281
Stars
0
Downloads
0
Weekly
0/5

What is Plate?

Plate is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to rich-text editor with ai and shadcn/ui

Rich-text editor with AI and shadcn/ui

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Rich-text editor with AI and shadcn/ui

Use Cases

Rich-text editing
AI-powered editor
React component library
udecode

Maintainer

LicenseNOASSERTION
Languagetypescript
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx plate

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Plate

Plate is an open-source, plugin-based rich-text editor framework for React built on Slate, with a companion MCP server that lets AI assistants inspect and apply Plate UI registry items — including editor templates, plugins, components, and documentation — directly into your project. The MCP server is powered by the shadcn CLI and gives AI coding tools like Claude, Cursor, and VS Code Copilot real access to Plate's component registry at platejs.org, enabling one-shot editor setup without manual copy-pasting of boilerplate. Teams building document editors, note-taking apps, or AI-powered writing tools use Plate for its shadcn/ui integration and extensible plugin architecture.

Prerequisites

  • Node.js 18 or higher installed
  • A React project with TypeScript (Plate components use TypeScript)
  • shadcn/ui configured in your project (Plate uses shadcn's registry and CLI)
  • An MCP-compatible AI coding client such as Cursor, VS Code with Copilot, or Claude
1

Set up a new Plate project or add to an existing one

Bootstrap a new Plate editor using the Notion-like starter template, or add Plate to an existing React project via the shadcn CLI.

npx shadcn@latest init
npx shadcn@latest add https://platejs.org/r/editor-basic
2

Configure the Plate MCP server in Cursor

Add the Plate MCP server to your Cursor project by creating or editing .cursor/mcp.json. The server uses the shadcn CLI to serve Plate's registry over the MCP protocol.

{
  "mcpServers": {
    "plate": {
      "description": "Plate editors, plugins and components",
      "type": "stdio",
      "command": "npx",
      "args": ["shadcn@latest", "mcp"]
    }
  }
}
3

Configure the Plate MCP server in VS Code

For VS Code with GitHub Copilot, create or edit .vscode/mcp.json to add the Plate registry server.

{
  "servers": {
    "plate": {
      "type": "stdio",
      "command": "npx",
      "args": ["shadcn@latest", "mcp"]
    }
  }
}
4

Configure the Plate MCP server in Claude

For Claude Desktop or Claude Code, add the server to your .mcp.json project file.

{
  "mcpServers": {
    "plate": {
      "description": "Plate editors, plugins and components",
      "type": "stdio",
      "command": "npx",
      "args": ["shadcn@latest", "mcp"]
    }
  }
}
5

Ask your AI assistant to scaffold or update Plate components

With the MCP server active, your AI assistant can read Plate's registry and apply components to your project without manual copy-pasting.

Plate Examples

Client configuration

Cursor MCP configuration to expose the Plate registry to AI coding assistants. Place this in .cursor/mcp.json at your project root.

{
  "mcpServers": {
    "plate": {
      "description": "Plate editors, plugins and components",
      "type": "stdio",
      "command": "npx",
      "args": ["shadcn@latest", "mcp"]
    }
  }
}

Prompts to try

Example prompts to use once the Plate MCP server is configured in your AI coding environment.

- "Set up a Plate editor with basic formatting and table support"
- "Help me understand how the Plate AI plugin works"
- "Update my editor components to the latest Plate version"
- "Add a code block plugin to my existing Plate editor"
- "Show me the available Plate editor templates"

Troubleshooting Plate

npx shadcn@latest mcp fails with 'cannot find module' or version errors

Ensure Node.js 18+ is installed. Clear your npx cache with 'npx clear-npx-cache' and try again. Pin to a specific shadcn version if the latest has breaking changes.

AI assistant cannot find Plate components in the registry

The registry is served from platejs.org/r/registry.json. Verify internet connectivity and that the MCP server process started without errors. Check the Cursor or VS Code MCP output panel for error messages.

Components are added but TypeScript errors appear in the project

Plate requires shadcn/ui to be initialized first. Run 'npx shadcn@latest init' to set up the project configuration, then re-apply the Plate components.

Frequently Asked Questions about Plate

What is Plate?

Plate is a Model Context Protocol (MCP) server that rich-text editor with ai and shadcn/ui It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Plate?

Follow the installation instructions on the Plate GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Plate?

Plate works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Plate free to use?

Yes, Plate is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "plate": { "command": "npx", "args": ["-y", "plate"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Plate?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides