How to Use the Canva MCP in Google ADK

Q: Can I limit which Canva tools my Google ADK agent can access?

Yes. When initializing the McpToolset in your Python code, use the optional tool names filter. This lets you restrict your Google ADK agent to safe operations like listdesigns while blocking destructive actions.

Q: How do I pass Canva assets to Google ADK using this MCP Server?

You run listassets to retrieve current media files, then pass those references directly to Gemini. The Google ADK handles the context transfer, allowing the model to analyze asset metadata alongside your BigQuery datasets.

Q: How does Google ADK handle long-context reasoning with Canva design data?

The agent uses getdesign to pull detailed structural data for multiple files. Gemini's million-token context window allows the Google ADK to analyze these layouts simultaneously, ensuring your brand guidelines are maintained across all assets.

Connect your Google ADK agents to this Canva MCP Server to generate, export, and organize enterprise assets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Canva MCP to Google ADK

Create your Vinkius account to connect Canva to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Canva with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context design mapping with Google ADK

The `list_designs` tool pulls your entire design catalog, including thumbnails and metadata. Because Gemini models in the Google ADK support massive context windows, your agent can process hundreds of design records simultaneously to plan complex marketing campaigns. The agent then runs `get_design` to extract deep structural details of specific files. This lets your enterprise agent cross-reference Canva layouts with customer data pulled directly from BigQuery.

Automated asset ingestion for Google Cloud pipelines

Your agent runs `upload_asset` to feed newly generated marketing graphics directly into your Canva storage context. This MCP tool enables automated uploads whenever your Vertex AI data pipeline outputs new product images. When an asset is no longer needed, the agent invokes `delete_asset` to maintain a clean workspace. This ensures your Canva asset library matches your Google Cloud storage state without manual cleanup.

High-volume exports managed by Google ADK

The `export_design` tool initiates the rendering of Canva designs into PDF, PNG, or MP4 formats. Your Google ADK agent triggers this process via the MCP Server, handling bulk export requests generated by your analytical models. To complete the process, the agent uses `get_export` to poll the job status and grab the final download link. You can then route this asset to Google Cloud Storage or distribute it directly to your enterprise users.

Setup guide

Set up Canva MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Canva tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Canva_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Canva tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Canva. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Canva now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Canva MCP in Google ADK

Yes. When initializing the `McpToolset` in your Python code, use the optional tool names filter. This lets you restrict your Google ADK agent to safe operations like `list_designs` while blocking destructive actions.

You run `list_assets` to retrieve current media files, then pass those references directly to Gemini. The Google ADK handles the context transfer, allowing the model to analyze asset metadata alongside your BigQuery datasets.

The agent uses `get_design` to pull detailed structural data for multiple files. Gemini's million-token context window allows the Google ADK to analyze these layouts simultaneously, ensuring your brand guidelines are maintained across all assets.

This integration supports both Stdio and HTTP transports. You initialize the toolset with the Vinkius HTTP endpoint, which the Google ADK uses to communicate with the Canva API.

Vinkius isolates the connection inside an ephemeral V8 sandbox. Your credentials never touch Google Cloud, and tools like `get_user` only access the specific organizational boundaries you explicitly authorize.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript