# How to Use Layerre with MCP

Connect Claude, Cursor, VS Code, and other MCP clients to Layerre. Import a Canva design from chat and render images or PDFs without leaving your editor.

The Model Context Protocol (MCP) lets an AI assistant call tools on your behalf. Layerre’s hosted MCP server turns that into a design workflow: import a Canva share link as a template, read its layers, and render PNG, JPEG, WebP, or PDF variants from chat in Cursor, Claude, VS Code, or Windsurf.

## What is MCP

MCP is an open standard for connecting AI assistants to external tools. Clients such as Claude, Cursor, and VS Code speak MCP over HTTP or stdio. Layerre exposes 13 tools on a remote Streamable HTTP server, so you add one URL, sign in with OAuth (or an API key), and the assistant works as you, inside your plan limits. The server cannot delete templates, change billing, or manage API keys.

## Use cases



## How it works

- 1. Add this URL in your MCP client (Cursor, Claude, VS Code, Windsurf, or mcp.json): https://mcp.layerre.com/mcp
- 2. Click Connect or Authenticate. Sign in to Layerre and allow access. OAuth is recommended; API keys work for CI
- 3. Ask the assistant to check your Layerre connection. It should call layerre_auth_status
- 4. Import a Canva share link, inspect layer IDs, then render variants with text or image overrides

## Example workflows



## Where to connect

The [MCP docs](/docs/mcp/) walk through setup for Cursor, Claude, VS Code, and Windsurf—install links where supported, JSON snippets where not. The server is [open source on GitHub](https://github.com/Layerre/layerre-mcp).

---

HTML version: https://layerre.com/integrations/mcp/