Ai Canvas Mcp (@aicanvas/mcp)

What is AI Canvas MCP?

AI Canvas MCP is a read-only Model Context Protocol server that lets AI editors (Claude Code, Codex, Cursor, etc.) search, inspect, and install animated React components, design systems, and templates from the AI Canvas catalog directly into a project. It serves developers who want to drop finished, open‑source UI code into their codebase or let their AI agent handle installation.

How to use AI Canvas MCP?

Connect the server to your AI editor with claude mcp add aicanvas -- npx -y @aicanvas/mcp or add it to your MCP configuration file. The server fetches the live registry at runtime and returns component source code and reproduction prompts. No additional setup is required; the server works out of the box with any MCP‑compatible editor.

Key features of AI Canvas MCP

• Read‑only server that fetches the live AI Canvas registry
• Lets AI agents search, inspect, and install components automatically
• Returns full React/TypeScript source code, not black‑box dependencies
• Supports reproduction prompts for Claude Code, Lovable, and V0
• Works with shadcn CLI, MCP, and direct prompt copying
• Open‑core: free components are MIT licensed; Premium is proprietary

Use cases of AI Canvas MCP

• Letting an AI agent install animated React components during a coding session
• Quickly adding a design system (e.g., Andromeda) or template to a new project
• Remixing a component by handing its reproduction prompt to a different AI editor

FAQ from AI Canvas MCP

What is the difference between AI Canvas MCP and the shadcn CLI?

The shadcn CLI installs components manually with npx shadcn@latest add @aicanvas/<slug>. AI Canvas MCP automates this by letting your AI editor search, inspect, and install components for you in the same way.

What runtime dependencies are required?

AI Canvas components are built with React, TypeScript, Tailwind CSS, and Framer Motion. 3D pieces use Three.js. They are designed for the Next.js App Router but work in any modern React setup.

Is AI Canvas MCP free?

Yes, the MCP server is free to use, and the free library of components is MIT licensed. Premium components, design systems, and templates are proprietary under the AI Canvas Premium License.

Where does the server fetch data from?

It fetches the live AI Canvas registry at runtime, so new components become available to your agent shortly after they are published. The server is read‑only and does not store any data locally.

What editors does AI Canvas MCP work with?

It works with any MCP‑compatible AI editor, including Claude Code, Codex, Cursor, and others.