# Canva MCP connector

The Canva connector brings your designs, brand templates, assets, comments and design analytics into Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent, so each person works with Canva as themselves, with every action logged.

Source: https://elaichi.ai/connectors/canvarest/

## Facts

| | |
| --- | --- |
| Application | Canva |
| Category | Design |
| AI tools | 64 |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Canva is connected

- How many people viewed the Q3 pitch deck this week?
- Fill the event flyer brand template with next week's webinar details.
- Reply to the open comments on the product launch banner.

## Connect Canva in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Canva.
2. Optionally set Share with, then press Connect.
3. Approve it in Canva. Canva's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Canva tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Canva MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Canva MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Canva MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Canva MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Canva MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Canva to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Canva tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Canva through Elaichi

### See which campaign designs people actually opened

Marketing. Ask how many people viewed the launch deck or the spring flyer, who those viewers were and how views moved over time. The answer comes from Canva design analytics for the designs you already own.

### Fill a pitch deck from a brand template

Sales. Give the agent the prospect's name, logo and numbers and it runs an autofill on the approved brand template. The rep gets an on-brand deck without opening the editor.

### Keep the brand template library in order

Creative. List every brand template, check which fields each one expects and create a new template when a campaign needs it. Teams fill templates instead of rebuilding from scratch.

### Upload venue photos and signage straight into Canva

Events. Drop a file or a link and the agent starts an upload job, then confirms when the asset is ready in Canva. Rename or remove assets once the event has passed.

### Reply to design comments without opening the file

Communications. Read a comment thread on the all-hands slides, draft a reply and post it. Feedback rounds close faster when the thread is handled from the same chat.

### Track whether new hires read the onboarding guide

People. Check views and page views on the onboarding design shared by link, and see which pages people stop on. Adjust the guide where readers drop off.

## Elaichi vs Zapier MCP vs Composio for Canva

All three can connect Canva to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Canva tools | Allow or restrict single Canva tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Canva call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Canva to Claude?

Connect Canva in Elaichi first: Canva opens its own sign-in screen, you approve access, and you are done, with no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. From that point Claude can read your Canva design analytics, assets, brand templates and comments as you. Short, concrete asks such as "views on the Q3 deck this week" work better than long sentences.

### Does Canva work with ChatGPT and Cursor as well as Claude?

Yes. Once Canva is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect Canva once and every client picks it up.

### What can an AI agent actually do with my Canva data?

With Canva connected, an agent can tell you how many people viewed a design, who they were and how views changed over time, including page views and link activity. It can upload a file or a link as a new Canva asset, rename or remove an asset, fill a brand template with your details, create a brand template and read or reply to comment threads on a design.

### Does connecting Canva give the AI everything in my Canva team?

No. Every call to Canva runs under the person who signed in, so the agent sees only the designs, assets and brand templates that person can already reach in Canva. Elaichi can narrow that further with restrictions, and it never widens what Canva itself allows.

### Can my team share one Canva connection?

Yes. One person connects Canva in Elaichi and shares it with a team, and nobody else ever handles a Canva credential. Each teammate still signs in to Elaichi as themselves, so the audit log names the actual person behind every Canva action.

### Can I stop an agent from deleting or changing things in Canva?

Yes. Restrictions in Elaichi work per action, so you can restrict deleting Canva assets or creating brand templates for a role or for one person while leaving read access alone. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it in Canva, whatever the prompt says.

### What happens to a Canva connection when someone leaves?

Offboarding that person in Elaichi ends their Canva access through every client at once. A Canva connection shared with a team keeps working for everyone else. If you want it gone entirely, disconnecting Canva once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

### Does the Canva MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Canva is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Canva?

Yes. Both let Claude, ChatGPT or Cursor use Canva. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Canva call.

### How is Elaichi different from Composio for Canva?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Canva: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 64 Canva tools

Every tool below is callable through https://api.elaichi.ai/mcp once Canva is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all Canva design analytics** (List). Gets the aggregated analytics for a design. The response includes total views, unique viewers, and view duration metrics. Requires the user to be in a Canva Enterprise organization. Preview API (may change without a new version). OAuth scope: design:content:read. Required: design_id.
- **List all Canva design analytics viewers** (List). Lists viewers for a design, ordered by most recent view first. Requires the user to be in a Canva Enterprise organization. Preview API (may change without a new version). OAuth scope: design:content:read. Required: design_id.
- **List all Canva design analytics views over time** (List). Lists the view counts over time for a design. Each response item represents one time bucket. Requires the user to be in a Canva Enterprise organization. Preview API (may change without a new version). OAuth scope: design:content:read. Required: design_id.
- **Canva design analytics page views search** (Search). Lists the page-level view duration data for a design. The request body can include page filters and pagination controls. Requires the user to be in a Canva Enterprise organization. Preview API (may change without a new version). OAuth scope: design:content:read. Required: design_id, page_ids.
- **List all Canva design analytics links** (List). Lists trackable links and their metrics for a design. Requires the user to be in a Canva Enterprise organization. Preview API (may change without a new version). OAuth scope: design:content:read. Required: design_id.
- **List all Canva app jwks** (List). Returns the Json Web Key Set (public keys) of an app. These keys are used to verify JWTs sent to app backends. Required: app_id.
- **Delete a Canva asset by ID** (Delete). You can delete an asset by specifying its assetId. This operation mirrors the behavior in the Canva UI. Deleting an item moves it to the trash. Deleting an asset doesn't remove it from designs that already use it. OAuth scope: asset:write. Required: id. id is the assetId.
- **Get single Canva asset by ID** (Get). You can retrieve the metadata of an asset by specifying its assetId. OAuth scope: asset:read. Required: id. id is the assetId.
- **Update a Canva asset by ID** (Update). You can update the name and tags of an asset by specifying its assetId. Updating the tags replaces all existing tags of the asset. OAuth scope: asset:write. Required: id. id is the assetId.
- **Create a Canva asset upload job** (Create). Starts a new asynchronous job to upload an asset to the user's content library. Supported file types for assets are listed in the Assets API overview. The request format for this endpoint is an application/octet-stream body of bytes. Attach information about the upload using an Asset-Upload-Metadata header. OAuth scope: asset:write. Required: truto_asset_upload_metadata, file.
- **Get single Canva asset upload job by ID** (Get). Get the result of an asset upload job that was created using the Create asset upload job API. You might need to make multiple requests to this endpoint until you get a success or failed status. For more information on the workflow for using asynchronous jobs, see API requests and responses. OAuth scope: asset:read. Required: id. id is the jobId.
- **Create a Canva URL asset upload job** (Create). Starts a new asynchronous job to upload an asset from a URL to the user's content library. Supported file types for assets are listed in the Assets API overview. OAuth scope: asset:write. Required: name, url.
- **Get single Canva URL asset upload job by ID** (Get). Get the result of an asset upload job that was created using the Create asset upload job via URL API. You might need to make multiple requests to this endpoint until you get a success or failed status. For more information on the workflow for using asynchronous jobs, see API requests and responses. OAuth scope: asset:read. Required: id. id is the jobId.
- **Create a Canva autofill job** (Create). Starts a new asynchronous job to autofill a Canva design using input data. Use the type field to choose the source of the design: - create_from_brand_template: autofill a new design from a brand template. If type isn't specified in the request, the request type is assumed to be create_from_brand_template. OAuth scope: design:content:write.
- **Get single Canva autofill job by ID** (Get). Get the result of a design autofill job that was created using the Create design autofill job API. You might need to make multiple requests to this endpoint until you get a success or failed status. For more information on the workflow for using asynchronous jobs, see API requests and responses. OAuth scope: design:meta:read. Required: id. id is the jobId.
- **List all Canva brand templates** (List). AVAILABILITY: To use this API, your app must act on behalf of a user that's on a Canva plan with access to brand templates (such as Canva Pro, Canva Teams, or Canva Enterprise). Get a list of the brand templates the user has access to. OAuth scope: brandtemplate:meta:read.
- **Create a Canva brand template** (Create). AVAILABILITY: To use this API, your app must act on behalf of a user that's on a Canva plan with access to brand templates (such as Canva Pro, Canva Teams, or Canva Enterprise). Additionally, the user must have one of the following roles: Team admin, Brand designer, Organization admin, or Organization designer. Preview API (may change without a new version). OAuth scope: brandtemplate:content:write. Required: design_id.
- **Get single Canva brand template by ID** (Get). AVAILABILITY: To use this API, your app must act on behalf of a user that's on a Canva plan with access to brand templates (such as Canva Pro, Canva Teams, or Canva Enterprise). Retrieves the metadata for a brand template. OAuth scope: brandtemplate:meta:read. Required: id. id is the brandTemplateId.
- **List all Canva brand template datasets** (List). AVAILABILITY: To use this API, your app must act on behalf of a user that's on a Canva plan with access to brand templates (such as Canva Pro, Canva Teams, or Canva Enterprise). Gets the dataset definition of a brand template. OAuth scope: brandtemplate:content:read. Required: brand_template_id.
- **Create a Canva comment** (Create). Create a new top-level comment on a design. For information on comments and how they're used in the Canva UI, see the Canva Help Center. A design can have a maximum of 1000 comments. OAuth scope: comment:write. Required: attached_to, message.
- **List all Canva comment replies** (List). Retrieves a list of replies for a comment or suggestion thread on a design. For information on comments and how they're used in the Canva UI, see the Canva Help Center. Preview API (may change without a new version). OAuth scope: comment:read. Required: design_id, thread_id.
- **Create a Canva comment reply** (Create). Creates a reply to a comment or suggestion thread on a design. To reply to an existing thread, you must provide the ID of the thread which is returned when a thread is created, or from the thread_id value of an existing reply in the thread. Each thread can have a maximum of 100 replies created for it. Preview API (may change without a new version). OAuth scope: comment:write. Required: design_id, thread_id, message_plaintext.
- **Get single Canva comment reply by ID** (Get). Gets a reply to a comment or suggestion thread on a design. For information on comments and how they're used in the Canva UI, see the Canva Help Center. Preview API (may change without a new version). OAuth scope: comment:read. Required: id, design_id, thread_id. id is the replyId.
- **Get single Canva comment thread by ID** (Get). Gets a comment or suggestion thread on a design. To retrieve a reply to a comment thread, use the Get reply API. For information on comments and how they're used in the Canva UI, see the Canva Help Center. Preview API (may change without a new version). OAuth scope: comment:read. Required: id, design_id. id is the threadId.
- **Create a Canva comment thread** (Create). Creates a new comment thread on a design. For information on comments and how they're used in the Canva UI, see the Canva Help Center. Preview API (may change without a new version). OAuth scope: comment:write. Required: design_id, message_plaintext.
- **List all Canva connect signing keys** (List). The Keys API (connect/keys) is a security measure you can use to verify the authenticity of webhooks you receive from the Canva REST APIs. The Keys API returns a JSON Web Key (JWK), which you can use to decrypt the webhook signature and verify it came from Canva and not a potentially malicious actor. Preview API (may change without a new version).
- **List all Canva designs** (List). Lists metadata for all the designs in a Canva user's projects. You can also: - Use search terms to filter the listed designs. - Show designs either created by, or shared with the user. - Sort the results. OAuth scope: design:meta:read.
- **Create a Canva design** (Create). Creates a new Canva design. To create a new design, you can: - Use a preset design type. - Set height and width dimensions for a custom design. NOTE: Custom designs can have a maximum area of 25,000,000 pixels squared (for example, 5000 × 5000 pixels). OAuth scope: design:content:write.
- **Get single Canva design by ID** (Get). Gets the metadata for a design. This includes owner information, URLs for editing and viewing, and thumbnail information. OAuth scope: design:meta:read. Required: id. id is the designId.
- **List all Canva design pages** (List). Lists metadata for pages in a design, such as page-specific thumbnails. For the specified design, you can provide offset and limit values to specify the range of pages to return. NOTE: Some design types don't have pages (for example, Canva docs). Preview API (may change without a new version). OAuth scope: design:content:read. Required: design_id.
- **List all Canva design export formats** (List). Lists the available file formats for exporting a design. OAuth scope: design:content:read. Required: design_id.
- **List all Canva design datasets** (List). Gets the dataset definition of a design. If the design contains autofill data fields, this API returns an object with the data field names and the type of data they accept. OAuth scope: design:content:read. Required: design_id.
- **Create a Canva print partner design** (Create). AVAILABILITY: This API is only available to Print Partners. Creates a new Canva design using a Print Partner product ID. Print partner proofing information (such as bleed and page constraints) can optionally be provided in the request. Preview API (may change without a new version). OAuth scope: design:content:write. Required: design_source.
- **Get single Canva print partner design by ID** (Get). AVAILABILITY: This API is only available to Print Partners. Gets the metadata for a design. This includes owner information, URLs for editing and viewing, and thumbnail information. Print partner proofing information (such as bleed and page constraints) isn't stored on Canva, so you can optionally provide it in the request. Preview API (may change without a new version). OAuth scope: design:meta:read. Required: id. id is the designId.
- **Create a Canva design generation job** (Create). Starts a new asynchronous job to generate a Canva design from a text brief. A successful job includes metadata for the generated design, which is saved to the user's Canva account. You can generate a document or presentation. For presentations, you can also provide an outline of the slides to generate. Preview API (may change without a new version). OAuth scope: design:content:write. Required: brief, design_type, outline.
- **Get single Canva design generation job by ID** (Get). Gets the status and result of a design generation job created using the Create design generation job API. You might need to make multiple requests until the job has a success or failed status. For more information on the workflow for using asynchronous jobs, see API requests and responses. Preview API (may change without a new version). OAuth scope: design:content:write. Required: id. id is the jobId.
- **Create a Canva design import job** (Create). Starts a new asynchronous job to import an external file as a new design in Canva. The request format for this endpoint has an application/octet-stream body of bytes, and the information about the import is provided using an Import-Metadata header. Supported file types for imports are listed in Design imports overview. OAuth scope: design:content:write. Required: truto_import_metadata, file.
- **Get single Canva design import job by ID** (Get). Gets the result of a design import job created using the Create design import job API. You might need to make multiple requests to this endpoint until you get a success or failed status. For more information on the workflow for using asynchronous jobs, see API requests and responses. OAuth scope: design:content:write. Required: id. id is the jobId.
- **Create a Canva URL import job** (Create). Starts a new asynchronous job to import an external file from a URL as a new design in Canva. Supported file types for imports are listed in Design imports overview. OAuth scope: design:content:write. Required: title, url.
- **Get single Canva URL import job by ID** (Get). Gets the result of a URL import job created using the Create URL import job API. You might need to make multiple requests to this endpoint until you get a success or failed status. For more information on the workflow for using asynchronous jobs, see API requests and responses. OAuth scope: design:content:write. Required: id. id is the jobId.
- **Create a Canva image to design import job** (Create). Starts a new asynchronous job to convert an image into an editable design in Canva, using Magic Layers. Elements in the image become separate editable layers in the resulting design. Provide the image as an asset that is already in the user's Canva account. Preview API (may change without a new version). OAuth scope: design:content:write. Required: image.
- **Get single Canva image to design import job by ID** (Get). Gets the result of an image-to-design import job created using the Create image-to-design import job API. You might need to make multiple requests to this endpoint until you get a success or failed status. For more information on the workflow for using asynchronous jobs, see API requests and responses. Preview API (may change without a new version). OAuth scope: design:content:write. Required: id. id is the jobId.
- **Create a Canva export job** (Create). Starts a new asynchronous job to export a file from Canva. Once the exported file is generated, you can download it using the URL(s) provided. The download URLs are only valid for 24 hours. The request requires the design ID and the exported file format type. OAuth scope: design:content:read. Required: design_id, format.
- **Get single Canva export job by ID** (Get). Gets the result of a design export job that was created using the Create design export job API. If the job is successful, the response includes an array of download URLs. Depending on the design type and export format, there is a download URL for each page in the design. The download URLs are only valid for 24 hours. OAuth scope: design:content:read. Required: id. id is the exportId.
- **Create a Canva print partner export job** (Create). AVAILABILITY: This API is only available to Print Partners. Starts a new asynchronous job to export a Print Partner file from Canva. Once the exported file is generated, you can download it using the URL(s) provided. The download URLs are only valid for 24 hours. Preview API (may change without a new version). OAuth scope: design:content:read. Required: design_id, format.
- **Delete a Canva folder by ID** (Delete). Deletes a folder with the specified folderID. Deleting a folder moves the user's content in the folder to the Trash and content owned by other users is moved to the top level of the owner's projects. OAuth scope: folder:write. Required: id. id is the folderId.
- **Get single Canva folder by ID** (Get). Gets the name and other details of a folder using a folder's folderID. OAuth scope: folder:read. Required: id. id is the folderId.
- **Update a Canva folder by ID** (Update). Updates a folder's details using its folderID. Currently, you can only update a folder's name. OAuth scope: folder:write. Required: id, name. id is the folderId.
- **Create a Canva folder** (Create). Creates a folder in one of the following locations: - The top level of a Canva user's projects (using the ID root), - The user's Uploads folder (using the ID uploads), - Another folder (using the parent folder's ID). When a folder is successfully created, the endpoint returns its folder ID, along with other information. OAuth scope: folder:write. Required: name, parent_folder_id.
- **List all Canva folder items** (List). Lists the items in a folder, including each item's type. Folders can contain: - Other folders. - Designs, such as Instagram posts, Presentations, and Documents (Canva Docs). - Image assets. - Brand templates. To include brand_template items in the response, you must explicitly specify it in the item_types parameter. OAuth scope: folder:read. Required: folder_id.
- ...and 14 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
