Connect
Optimize
Secure
Live 26 Actions
Canva MCP Server
for AI Agents
Connect your AI agent to StackOne's Canva MCP server and give it 26 MCP tools out of the box. Auth, tool execution, and security all managed.
Canva MCP Server
Built by 
StackOne
StackOne 
Coverage
26 Agent Actions
Create, read, update, and delete across Canva — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Canva MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Canva tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Canva call.
Tools Discovery →What is the Canva MCP Server?
A Canva MCP server lets AI agents read and write Canva data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Canva MCP server ships with 26 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Canva MCP Tools
Every action from Canva's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Designs
- Create Design
Create a new Canva design
- List Designs
List designs owned by the authenticated user
- Get Design
Retrieve a design by its ID
Design Pages
- List Design Pages
List pages in a design
Folder Items
- List Folder Items
List items in a folder
- Move Folder Item
Move an item to a different folder
Folders
- Create Folder
Create a new folder
- Get Folder
Retrieve a folder by its ID
- Update Folder
Update a folder's name
- Delete Folder
Delete a folder
Assets
- Get Asset
Retrieve an asset by its ID
- Update Asset
Update an asset's metadata
- Delete Asset
Delete an asset
Asset Upload Jobs
- Create Asset Upload Job
Start an asset upload job via URL
- Get Asset Upload Job
Get the status and result of an asset upload job
Jobs
- Create Export Job
Start a design export job
- Get Export Job
Get the status and result of an export job
Comment Threads
- Create Comment Thread
Create a new comment thread on a design
- Get Comment Thread
Retrieve a comment thread from a design
Replys
- Create Reply
Add a reply to a comment thread
Replies
- List Replies
List replies in a comment thread
Current Users
- Get Current User
Retrieve the authenticated user's information
User Profiles
- Get User Profile
Retrieve the authenticated user's profile
Brand Templates
- Publish Brand Template
Publish a design as a brand template
- List Brand Templates
List brand templates owned by the authenticated user
- Get Brand Template
Retrieve a brand template by its ID
Set Up Your Canva MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Canva in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Check More Design & Visual MCP Servers
Webflow
98+ actions
Miro
86+ actions
Autodesk
51+ actions
Google Slides
47+ actions
Figma
44+ actions
Platform Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
Canva MCP Server FAQ
Does StackOne have a Canva MCP server?
Yes. StackOne offers a hosted Canva MCP server with 26 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Canva MCP server vs direct API integration — what's the difference?
A Canva MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Canva. A Canva MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Canva at runtime. StackOne provides both.
How does Canva authentication work for AI agents?
Canva authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Canva account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Canva MCP tools vulnerable to prompt injection?
Yes — Canva MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Canva agent and how do I avoid it?
Context bloat happens when Canva tool schemas and API responses eat your Canva agent's memory, preventing it from reasoning effectively. A single Canva query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Canva agent can access?
Yes — you can limit which actions your Canva agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Canva MCP server?
Yes — you can create custom agent actions for your Canva MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Canva's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Canva MCP server?
Skip a Canva MCP server if your integration is purely software-to-software — direct Canva API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Canva actions at runtime.
What AI frameworks and AI clients does the StackOne Canva MCP server support?
The StackOne Canva MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.