Canva Universal MCP Server

What is Canva Universal MCP Server about?

Provides a unified API layer that lets developers call Canva's design and media capabilities through the Model Context Protocol, ensuring compatibility with other MCP‑compliant services.

How to use Canva Universal MCP Server?

1. Prerequisites – Install Python 3.11+ and the uv package manager (pip install uv).
2. Install dependencies – Run uv sync to create a virtual environment and pull all libraries from pyproject.toml.
3. Activate the environment – source .venv/bin/activate (Linux/macOS) or .venv\Scripts\Activate (Windows PowerShell).
4. Start the MCP inspector – mcp dev src/universal_mcp_canva/server.py. Note the displayed address and port.
5. Install the application – mcp install src/universal_mcp_canva/server.py.
6. Consume the service – Enable Canva from the AgentR UI at https://agentr.dev/apps and interact through the provided API endpoints.

Key Features

• Full compliance with the MCP specification for seamless integration.
• Ready‑to‑use tool list documented in src/universal_mcp_canva/README.md.
• Simple local development workflow using uv and the MCP CLI.
• MIT‑licensed, easy to extend or embed in other Python projects.

Use Cases

• Building custom design automation bots that generate Canva graphics on demand.
• Integrating Canva editing capabilities into internal company portals or SaaS platforms.
• Enabling AI agents to create or modify visual content through a standardized protocol.
• Rapid prototyping of design‑centric features without dealing with Canva's native SDKs.

FAQ

Q: Do I need a Canva account or API key? A: Yes. The server expects relevant Canva credentials (e.g., API token) to be set in the .env file before starting the inspector.

Q: Can I run this on Windows? A: Absolutely. Just follow the Windows‑specific activation command (.venv\Scripts\Activate) and the rest of the steps are identical.

Q: Is Docker support available? A: The repository does not include a Dockerfile, but the server can be containerized by installing the same Python dependencies inside a base image.

Q: How do I add new tools? A: Extend src/universal_mcp_canva/app.py with additional functions and document them in the tools README.

Q: Where do I report bugs or request features? A: Open an issue on the GitHub repository https://github.com/universal-mcp/canva.

Canva Universal MCP Server

This repository contains an implementation of an Canva Universal MCP (Model Context Protocol) server. It provides a standardized interface for interacting with Canva's tools and services through a unified API.

The server is built using the Universal MCP framework.

This implementation follows the MCP specification, ensuring compatibility with other MCP-compliant services and tools.

Usage

You can start using Canva directly from agentr.dev. Visit agentr.dev/apps and enable Canva.

If you have not used universal mcp before follow the setup instructions at agentr.dev/quickstart

Available Tools

The full list of available tools is at ./src/universal_mcp_canva/README.md

Local Development

📋 Prerequisites

Ensure you have the following before you begin:

• Python 3.11+ (recommended)
• uv (install globally with pip install uv)

🛠️ Setup Instructions

Follow the steps below to set up your development environment:

1. Sync Project Dependencies

   uv sync
   

   This installs all dependencies from pyproject.toml into a local virtual environment (.venv).

2. Activate the Virtual Environment

   For Linux/macOS:

   source .venv/bin/activate
   

   For Windows (PowerShell):

   .venv\Scripts\Activate
   

3. Start the MCP Inspector

   mcp dev src/universal_mcp_canva/server.py
   

   This will start the MCP inspector. Make note of the address and port shown in the console output.

4. Install the Application

   mcp install src/universal_mcp_canva/server.py
   

📁 Project Structure

.
├── src/
│   └── universal_mcp_canva/
│       ├── __init__.py       # Package initializer
│       ├── server.py            # Server entry point
│       ├── app.py            # Application tools
│       └── README.md         # List of application tools
├── tests/                    # Test suite
├── .env                      # Environment variables for local development
├── pyproject.toml            # Project configuration
└── README.md                 # This file

📄 License

This project is licensed under the MIT License.

---

Generated with MCP CLI — Happy coding! 🚀