Canvelete MCP Server

Model Context Protocol (MCP) server for the Canvelete design platform. This server exposes Canvelete's design capabilities to AI assistants and other MCP-compatible clients, enabling programmatic design creation and manipulation.

🔗 Links:

• Canvelete Platform - Create designs online

• Documentation - Full API and platform documentation

• Get API Key - Generate your API key

📚 MCP Server Documentation:

• Element Types Guide - Complete guide to all 13 element types (including QR codes & barcodes), their capabilities, and styling limits

• Asset Search Guide - How to search and use external assets (Pixabay, Unsplash, Iconify, cliparts, illustrations)

• Examples - Practical examples and use cases

• MCP Setup Guide - Configuration and usage instructions

Quick Start

Then configure your MCP client (Claude Desktop, Kiro, etc.) with:

Related MCP server: figma-mcp

Features

Resources (Read-Only Data Access)

• Designs: Access user designs, browse templates

• Canvas: View canvas state and elements

• Assets: Browse user's asset library and available fonts

• User: Access profile and preferences

• Metadata: Complete element capabilities, styling limits, and design system documentation

Tools (Actions)

• Design Management: Create, update, delete, duplicate, and export designs

• Canvas Manipulation: Add, update, delete elements; resize canvas; clear canvas

  • 13 Element Types: rectangle, circle, text, image, svg, line, polygon, star, qr, barcode, table, container, bezier

  • QR Codes: Generate QR codes for URLs, vCards, WiFi, and more

  • Barcodes: Support for CODE128, EAN13, UPC, and 7 other formats

• Templates: List, apply, and create templates

• Assets: Comprehensive asset search across multiple sources

  • Pixabay: 2.7M+ free stock photos and illustrations

  • Unsplash: 3M+ high-quality curated photos

  • Iconify: 200K+ icons from 150+ icon sets

  • Cliparts: 10K+ curated clipart graphics

  • Illustrations: 5K+ artistic illustrations

• Fonts: 30+ professional fonts with metadata and pairing recommendations

• Shapes: 70+ SVG shapes from 8 categories (basic, arrows, stars, callouts, nature, symbols, geometric, extra)

• AI Integration: Access Civi AI for design generation

Available Prompts

Prompts provide guided templates for common design tasks:

• create_social_post - Create social media posts (Instagram, Facebook, Twitter, etc.)

• create_presentation_slide - Create presentation slides with title and content

• add_text_element - Add styled text elements to designs

Prompts help AI assistants create designs with proper structure and styling automatically.

Installation

Method 1: Global Installation (Recommended)

Install the package globally to use the canvelete-mcp command:

Method 2: NPX (No Installation Required)

Use npx to run without installing:

Method 3: Local Development

For development or custom builds:

Then use the local build path in your MCP configuration.

Configuration

Environment Variables

Create a .env file in the mcp-server directory:

Authentication

You need a Canvelete API key to use the MCP server:

1. Log in to your Canvelete account

2. Go to Settings → API Keys

3. Generate a new API key

4. Save the key securely

For detailed API documentation, see docs.canvelete.com.

You can provide the API key in two ways:

Option 1: Environment Variable (recommended for Claude Desktop)

Option 2: Tool Arguments (for programmatic use)

Configuration

Claude Desktop

1. Find your Claude Desktop config file:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

   • Windows: %APPDATA%\Claude\claude_desktop_config.json

   • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add the Canvelete server configuration:

Option A: Using Global Installation

Option B: Using NPX (No Installation)

Option C: Using Local Build

3. Restart Claude Desktop

Kiro

1. Find your Kiro config file: ~/.kiro/settings/mcp.json

2. Add the same configuration as above

3. Restart Kiro

Other MCP Clients

Any MCP-compatible client can use this server. Configure it to run:

• Command: canvelete-mcp (if installed globally) or npx -y @canveletedotcom/mcp-server

• Args: ["start"]

• Environment: Set CANVELETE_API_KEY and optionally CANVELETE_API_URL

Usage Examples

Example Conversations

Once configured, you can ask your AI assistant:

• "What designs do I have in Canvelete?"

• "Create a new 1080x1080 Instagram post design called 'Summer Sale'"

• "Add a text element to design {id} that says 'Hello World'"

• "Export design {id} as PNG"

• "List all my uploaded assets"

• "Apply template {template-id} to design {design-id}"

• "Create a presentation slide with title 'Welcome' and subtitle 'Introduction'"

• "Search for stock images of mountains"

Quick Example: Create a Social Media Post

See EXAMPLES.md for more detailed examples. For complete API documentation, visit docs.canvelete.com.

Available Resources

Resources provide read-only access to Canvelete data:

Available Tools

Design Management Tools

• list_designs - List all user's designs with pagination and search

• get_design - Get detailed design info including canvas data

• create_design - Create new design with custom dimensions

• update_design - Update design properties (name, description, visibility)

• delete_design - Delete a design permanently

• duplicate_design - Fork/copy an existing design

• export_design - Export design to PNG, JPG, PDF, or SVG format

Canvas Manipulation Tools

• add_element - Add any element type (shape, text, image, SVG, etc.)

• update_element - Modify element properties (position, style, content)

• delete_element - Remove an element from canvas

• resize_canvas - Change canvas dimensions

• clear_canvas - Remove all elements from canvas

Template Tools

• list_templates - Browse available design templates

• apply_template - Apply a template to an existing design

• create_template - Save a design as a reusable template

Asset Management Tools

• list_assets - View user's asset library (images, fonts, etc.)

• search_stock_images - Search Pixabay for stock images

• search_icons - Search for icon assets

• search_clipart - Search for clipart images

• search_illustrations - Search for illustration assets

• list_fonts - List available fonts by category

• upload_asset - Upload a new asset to the library

AI Tools

• generate_design - Generate designs using AI

• chat_with_civi - Interact with Civi AI for design assistance

Element Types

Supported canvas element types:

• rectangle - Rectangular shapes

• circle - Circular/elliptical shapes

• text - Text elements with fonts

• image - Images from URLs or assets

• line - Straight lines

• polygon - Multi-sided shapes

• star - Star shapes

• svg - SVG graphics

• bezier - Curved paths

• container - Group elements

• table - Data tables

Development

Build

Run in Development

Type Check

Clean Build

MCP Protocol Compliance

This server follows the MCP Protocol specification (2025-11-25).

Compliance Documentation:

• MCP_COMPLIANCE.md - Implementation best practices and protocol compliance

• SPECIFICATION_COMPLIANCE.md - Detailed compliance with official MCP specification (2025-11-25)

Key Compliance Features:

• ✅ All logging uses stderr (never stdout) to avoid corrupting JSON-RPC messages

• ✅ Proper error handling and formatting

• ✅ Complete tool, resource, and prompt definitions

• ✅ Standard MCP server structure and initialization

Testing Compliance:

Troubleshooting

"Invalid API key"

• Generate a new API key in Canvelete Settings → API Keys

• Verify the key is set correctly in your MCP config

• Check key hasn't expired or been revoked

• Run the test script to verify: npx tsx test-auth.ts your_api_key

"Permission denied"

• Ensure API key has appropriate scopes

• Verify you own the resource you're modifying

"Failed to connect to API"

• Check CANVELETE_API_URL is correct (default: https://www.canvelete.com)

• Verify network connectivity to the Canvelete API

• For local development, ensure the Canvelete app is running

Claude Desktop doesn't show resources

• Restart Claude Desktop

• Check the config file syntax

• Verify the server path is absolute

• Check stderr logs for errors

Real-time Sync

The MCP server supports real-time synchronization with the design editor via WebSocket. When you make changes through MCP tools, the editor will instantly update to reflect those changes.

Setup

1. Start the WebSocket server (in the main Canvelete directory):

2. The WebSocket server runs on port 3001 by default. You can change this with the WS_PORT environment variable.

3. Open the design editor - you'll see a sync indicator in the top-right corner showing connection status.

How it works

• When MCP tools modify a design (add/update/delete elements, resize canvas, etc.), the changes are broadcast via WebSocket

• All connected editor clients subscribed to that design receive instant updates

• The editor shows a "Live" indicator when connected, with a count of received updates

Environment Variables

Security & Privacy

API Key Security

• Never commit API keys to version control or share them publicly

• Use environment variables or secure configuration files

• Rotate keys regularly if compromised or exposed

• Use separate keys for development and production

Data Privacy

• The MCP server accesses your Canvelete account data through API keys

• All API communication uses HTTPS encryption

• API keys have scoped permissions based on your account settings

• Review your API key permissions in Canvelete Settings → API Keys

Rate Limiting

• API keys may have rate limits based on your subscription plan

• The server respects rate limits and will return appropriate errors

• Check your subscription plan for rate limit details

Best Practices

• Only use trusted API keys from your own account

• Don't share your API keys with untrusted parties

• Monitor your API usage in Canvelete dashboard

• Report security issues to security@canvelete.com (do not open public issues)

Deployment Modes

The Canvelete MCP Server supports both local and cloud deployment. See DEPLOYMENT.md for detailed deployment instructions.

Local Deployment (Default)

The server runs locally on your machine using stdio transport, which is the standard for MCP clients like Claude Desktop, Kiro, and Cursor.

Advantages:

• ✅ Full control over your environment

• ✅ No network latency

• ✅ Data stays on your machine

• ✅ Simple setup and configuration

• ✅ Works offline (once API key is cached)

Use Cases:

• Personal development

• Testing and debugging

• Privacy-sensitive workflows

• Desktop applications (Claude Desktop, Cursor, etc.)

Cloud Deployment

The server can be deployed to cloud platforms using containerization or serverless functions. The stdio transport works seamlessly in cloud environments.

Advantages:

• ✅ Scalable and always available

• ✅ No local resource usage

• ✅ Accessible from multiple devices

• ✅ Managed infrastructure

• ✅ Easy updates and maintenance

Supported Platforms:

• Docker/Containers: Deploy to any container platform (Docker, Kubernetes, etc.)

• Google Cloud Run: Serverless container platform

• Azure Functions: Serverless with custom handlers

• AWS Lambda: Serverless functions (with stdio adapter)

• Vercel/Netlify: Serverless platforms

• Any Node.js hosting: Railway, Render, Fly.io, etc.

Quick Cloud Examples:

See DEPLOYMENT.md for complete deployment guides for:

• Docker/Containers (Dockerfile included)

• Google Cloud Run

• Azure Functions

• AWS Lambda

• Railway, Render, Fly.io

• Vercel/Netlify

Requirements

• Node.js: >= 18.0.0

• Canvelete Account: Sign up at canvelete.com

• Canvelete API Key: Get one from Canvelete Settings → API Keys

• Documentation: See docs.canvelete.com for API reference

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

Quick steps:

1. Fork the repository

2. Create your feature branch (git checkout -b feature/amazing-feature)

3. Commit your changes (git commit -m 'Add some amazing feature')

4. Push to the branch (git push origin feature/amazing-feature)

5. Open a Pull Request

For detailed contribution guidelines, code standards, and development setup, see CONTRIBUTING.md.

Changelog

See CHANGELOG.md for a detailed list of changes and version history.

License

MIT License - see LICENSE file for details.

Support

For issues and questions:

• GitHub Issues: canvelete/canvelete/issues

• Platform Documentation: docs.canvelete.com

• Canvelete Platform: canvelete.com

• API Documentation: docs.canvelete.com/api

• Get Help: Visit canvelete.com/support or docs.canvelete.com/help

Deployment Architecture

How It Works

The MCP server uses stdio transport by default, which works in both local and cloud environments:

1. Local Mode: MCP clients (Claude Desktop, etc.) spawn the server process and communicate via stdin/stdout

2. Cloud Mode: Cloud platforms run the server in containers/functions and handle stdio communication through their infrastructure

Data Flow

• MCP Protocol: JSON-RPC over stdio (local) or HTTP/SSE (cloud)

• Canvelete API: Always HTTPS to https://canvelete.com

Choosing Deployment Mode

Use Local Deployment if:

• You're using Claude Desktop, Cursor, or other desktop MCP clients

• You want maximum privacy and control

• You're developing or testing

• You have a single user/machine

Use Cloud Deployment if:

• You need 24/7 availability

• You want to share access across multiple devices

• You need scalability for multiple users

• You prefer managed infrastructure

Related Links

Canvelete Resources

• Canvelete Platform - Create and edit designs online

• Documentation - Complete platform and API documentation

• API Reference - Detailed API documentation

• Get Started Guide - Platform getting started guide

MCP Resources

• MCP Server Directory

• Model Context Protocol Documentation

• MCP Cloud Deployment Guide