plate-playground-template
Plate AI template with React 19, Next 16, Tailwind 4, MCP.
claude mcp add --transport stdio udecode-plate-playground-template bun dev \ --env UPLOADTHING_TOKEN="your-uploadthing-api-token" \ --env AI_GATEWAY_API_KEY="your-ai-gateway-api-key"
How to use
This MCP server hosts the Plate Playground template, a Next.js 16 project that integrates Plate AI, plugins, and components for building rich content editors. The server exposes a development environment where you can start the app with bun dev and access the editor UI at the editor route (http://localhost:3000/editor). The setup includes the Plate editor within a Next.js app, styled with shadcn/ui, and wired to MCP capabilities to enable component collaboration, AI-assisted editing, and plugin-driven workflows. Use the provided environment variables to connect to AI gateway services and UploadThing for media/assets management. Once running, you can customize the editor experience, experiment with Plate’s MCP features, and iterate on plugins and components directly in the template.
How to install
Prerequisites:
- Node.js 20+ (or ensure bun is installed and available as bun)
- bun package manager
Installation options:
Option 1: Using CLI (Recommended)
- Run the CLI command to add the Plate editor AI package to a project: npx shadcn@latest add @plate/editor-ai
Option 2: Using the Template
- Use the provided template to create a new project (via GitHub template): Use this template: https://github.com/udecode/plate-playground-template/generate
- Then install dependencies: bun install
After installation, copy the example environment file and configure the needed keys as described in the Development steps (AI_GATEWAY_API_KEY and UPLOADTHING_TOKEN). Then start the development server with bun dev.
To run the server:
- Ensure you are in the project directory
- Run: bun dev
Open http://localhost:3000/editor to view the editor.
Additional notes
Tips and notes:
- Prerequisites mention Node.js 20+ and bun; using bun is common for this template.
- AI_GATEWAY_API_KEY and UPLOADTHING_TOKEN must be supplied in .env.local (as shown in .env.example) to enable AI features and media uploads.
- The editor URL is /editor; you can customize routes or components within the Next.js app to suit your MCP workflow.
- If you encounter port conflicts, check that the dev server is listening on the expected port (default 3000).
- This template emphasizes Plate integration; explore adding or configuring MCP-enabled components and plugins to extend editor capabilities.
Related MCP Servers
plate
Rich-text editor with AI, MCP, and shadcn/ui
next-devtools
Next.js Development for Coding Agent
ragrabbit
Open Source, Self-Hosted, AI Search and LLM.txt for your website
turn-based-game
A turn-based games app built with Next.js and TypeScript that features Tic-Tac-Toe and Rock Paper Scissors games with AI opponents powered by the Model Context Protocol (MCP), offering three difficulty levels.
alris
Alris is an AI automation tool that transforms natural language commands into task execution.
google-earth-engine
MCP server for Google Earth Engine. Query Google Earth Engine with natural language. Fetch datasets, run tasks and visualize in chat.