> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to DynaPictures

The DynaPictures connector lets your AI agent act in each user's DynaPictures account. Each user connects their own DynaPictures access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 17 tools.

**Authentication:** Bearer Token
**Categories:** Design, Marketing
**Tools:** 17: 6 read, 7 write, 4 destructive
**Users sign in with:** Access token
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=DYNAPICTURES)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the DynaPictures connection

   In **AgentKit > Connections**, create a DynaPictures connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'dynapictures'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize DynaPictures:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'dynapictures_templates_list',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "dynapictures"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize DynaPictures:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="dynapictures_templates_list",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their DynaPictures credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'dynapictures_ai_image_job_get',
  toolInput: {
    job_uid: '<job_uid>',
  },
  connector: 'dynapictures',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="dynapictures_ai_image_job_get",
    tool_input={
        "job_uid": "<job_uid>",
    },
    connection_name="dynapictures",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `dynapictures_ai_image_job_get`

Get AI Image Job · Read-only

Get the status and result of an AI image generation job.
Returns jobUid, status (queued, running, done or error), resultUrl when done, creditsCharged, creditsRemaining and error when it failed.
Poll this after dynapictures_ai_image_generate. Download the resultUrl image if you need to keep it.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `job_uid` (`string`, required): jobUid returned by dynapictures_ai_image_generate. Example: aBcD1234eFgH5678iJkL9012.

Example input: `{"job_uid":"<job_uid>"}`

### `dynapictures_media_asset_get`

Get Media Asset · Read-only

Get one media library asset.
Returns id, folder, mimeType, filename, size, url, thumbnailUrl, dateCreated and dateUpdated.
Use dynapictures_media_assets_list to find asset IDs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `asset_id` (`string`, required): ID of the asset. Example: 5a12844966.
- `workspace_id` (`string`, required): ID of the workspace, from dynapictures_workspaces_list. Example: 8eb9e4869b.

Example input: `{"asset_id":"<asset_id>","workspace_id":"<workspace_id>"}`

### `dynapictures_media_assets_list`

List Media Assets · Read-only

List the images and folders in a workspace's media library, 30 per page.
Returns page, totalPages and results with id, folder, mimeType, filename, size, url, thumbnailUrl, dateCreated and dateUpdated.
Use asset URLs as imageUrl values in dynapictures_image_generate.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `workspace_id` (`string`, required): ID of the workspace, from dynapictures_workspaces_list. Example: 8eb9e4869b.
- `page` (`integer`, optional): Page number, starting at 1. Example: 1.

Example input: `{"workspace_id":"<workspace_id>"}`

### `dynapictures_template_get`

Get Template · Read-only

Get one design template with its layers.
Returns id, name, thumbnail, dateCreated, dateUpdated and layers with type, name, width and height.
Use this to see which layer names to customize in dynapictures_image_generate.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `template_id` (`string`, required): ID of the design template, shown in the top-left corner of the template page or returned by dynapictures_templates_list. Example: debcaw6f99.

Example input: `{"template_id":"<template_id>"}`

### `dynapictures_templates_list`

List Templates · Read-only

List the design templates that are ready for API use (the Sync to Zapier option is on).
Returns templates with id, name, thumbnail, dateCreated, dateUpdated and layers (type, name, width, height).
Use this to find template IDs and layer names before dynapictures_image_generate. Use dynapictures_template_get for one template.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `dynapictures_workspaces_list`

List Workspaces · Read-only

List the workspaces the API key's user is a member of.
Returns workspaces with id, name, dateCreated and dateUpdated.
Use this to find a workspace ID for the media library tools.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `dynapictures_ai_image_generate`

Start AI Image Generation · Write

Start an AI image generation job from a text prompt, optionally editing a source photo or using named reference images.
Returns jobUid and status queued (HTTP 202).
Poll dynapictures_ai_image_job_get with the jobUid until status is done. Uses AI credits that depend on the model; a 4xx means the job was not queued.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `model_id` (`string`, required): AI model to use, for example gemini-3.1-flash-image (Nano Banana), nano-banana-pro, gpt-image-1-mini, gpt-image-2-low, gpt-image-2-med or flux-2-pro. See https://dynapictures.com/docs/ for the list and credit costs. Example: gemini-3.1-flash-image.
- `prompt` (`string`, required): Text prompt describing the image. Reference images by [name] tokens. Example: A photorealistic cup of coffee on a wooden table, soft morning light.
- `ratio` (`string`, optional): Aspect ratio. Default 1:1; supported ratios vary by model. Example: 16:9. One of: `1:1`, `3:2`, `2:3`, `16:9`, `9:16`, `4:3`, `3:4`.
- `reference_images` (`array`, optional): Named reference images, each with a name (used as [name] in the prompt) and a public url. At most 6 input images in total including source_image. Example: [{"name": "logo", "url": "https://example.com/logo.png"}]
- `source_image` (`string`, optional): URL of a photo to edit (image-to-image). Leave empty for text-to-image. Editing models only. Example: https://example.com/product.jpg.

Example input: `{"model_id":"<model_id>","prompt":"<prompt>"}`

### `dynapictures_image_generate`

Generate Image · Write

Generate an image from a DynaPictures design template, replacing text, images and styling in its layers.
Returns id, templateId, imageUrl, thumbnailUrl, retinaThumbnailUrl, metadata, width and height.
Use this for single-page templates. Use dynapictures_multipage_images_generate for multi-page templates, dynapictures_pdf_generate for a PDF and dynapictures_templates_list to find template IDs and layer names. Each image uses one credit.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `template_id` (`string`, required): ID of the design template, shown in the top-left corner of the template page or returned by dynapictures_templates_list. Example: debcaw6f99.
- `format` (`string`, optional): Image file format. Default is the template's format. Example: png. One of: `png`, `jpeg`, `webp`, `avif`.
- `metadata` (`string`, optional): Custom text stored with the generated image and returned in the response and webhooks. Example: Post for @acme on Monday.
- `params` (`array`, optional): Layers to customize. Each layer object names the layer to change (name, as shown in the template's settings panel) and its new values: text and color for text layers; imageUrl plus optional imagePosition, imageAlignH and imageAlignV for image layers; and styling such as backgroundColor, borderColor, borderWidth, borderRadius and opacity. Example: [{"name": "title", "text": "Summer Sale", "color": "#333"}, {"name": "image1", "imageUrl": "https://example.com/photo.jpg"}]

Example input: `{"template_id":"<template_id>"}`

### `dynapictures_multipage_images_generate`

Generate Multipage Images · Write

Generate one image per page from a multi-page DynaPictures design template, customizing each page's layers.
Returns templateId, templateName and pages, each with id, imageUrl, thumbnailUrl, width, height and pageIndex.
Use this for carousels and multi-page designs. Use dynapictures_pdf_generate to get one PDF instead. Each page uses one credit.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `pages` (`array`, required): Pages to customize. Each page has its zero-based index and a layers array. Each layer object names the layer to change (name, as shown in the template's settings panel) and its new values: text and color for text layers; imageUrl plus optional imagePosition, imageAlignH and imageAlignV for image layers; and styling such as backgroundColor, borderColor, borderWidth, borderRadius and opacity. Example: [{"index": 0, "layers": [{"name": "text1", "text": "Page one title"}]}, {"index": 1, "layers": [{"name": "image4", "imageUrl": "https://example.com/photo.jpg...
- `template_id` (`string`, required): ID of the design template, shown in the top-left corner of the template page or returned by dynapictures_templates_list. Example: debcaw6f99.
- `format` (`string`, optional): Image file format for every page. Example: jpeg. One of: `png`, `jpeg`, `webp`, `avif`.
- `metadata` (`string`, optional): Custom text stored with the generated images. Example: Carousel for campaign 42.

Example input: `{"pages":[],"template_id":"<template_id>"}`

### `dynapictures_pdf_generate`

Generate PDF · Write

Generate a single PDF from a multi-page DynaPictures design template, customizing each page's layers.
Returns id, templateId, templateName, pdfUrl (also imageUrl), thumbnailUrl, metadata, width and height.
Use this for brochures, certificates and other multi-page documents. Use dynapictures_multipage_images_generate for separate images. Each page uses one credit.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `pages` (`array`, required): Pages to customize. Each page has its zero-based index and a layers array. Each layer object names the layer to change (name, as shown in the template's settings panel) and its new values: text and color for text layers; imageUrl plus optional imagePosition, imageAlignH and imageAlignV for image layers; and styling such as backgroundColor, borderColor, borderWidth, borderRadius and opacity. Example: [{"index": 0, "layers": [{"name": "text1", "text": "Page one title"}]}, {"index": 1, "layers": [{"name": "image4", "imageUrl": "https://example.com/photo.jpg...
- `template_id` (`string`, required): ID of the design template, shown in the top-left corner of the template page or returned by dynapictures_templates_list. Example: debcaw6f99.
- `metadata` (`string`, optional): Custom text stored with the generated PDF. Example: Certificate for Jane Doe.

Example input: `{"pages":[],"template_id":"<template_id>"}`

### `dynapictures_webhook_subscribe`

Subscribe Webhook · Write

Subscribe a URL to receive a notification each time a new image is generated from a template.
Returns the subscription with targetUrl, eventType, templateId, id and dateCreated.
Use dynapictures_webhook_unsubscribe with the same values to stop it.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `target_url` (`string`, required): URL of your endpoint that receives the new-image notifications. Example: https://example.com/webhooks/dynapictures.
- `template_id` (`string`, required): ID of the design template whose new images trigger the webhook. Example: 000d61e4f7.

Example input: `{"target_url":"<target_url>","template_id":"<template_id>"}`

### `dynapictures_workspace_create`

Create Workspace · Write

Create a new workspace, for example one per client.
Returns the workspace with id, name, dateCreated and dateUpdated.
Only account admins can create workspaces.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `name` (`string`, required): Name of the new workspace. Example: Banners for client 22.

Example input: `{"name":"<name>"}`

### `dynapictures_workspace_update`

Rename Workspace · Write

Rename a workspace.
Returns the workspace with id, name, dateCreated and dateUpdated.
Only account admins can modify workspaces.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `name` (`string`, required): New name of the workspace. Example: Banners for client 1234.
- `workspace_id` (`string`, required): ID of the workspace to rename, from dynapictures_workspaces_list. Example: 74b5b2c96a.

Example input: `{"name":"<name>","workspace_id":"<workspace_id>"}`

### `dynapictures_image_delete`

Delete Generated Image · Destructive

Delete a previously generated image from DynaPictures' servers.
Returns 200 with no body.
Take the two path parts from the image URL: for https://edge.dynapictures.com/ff01d10f8d/9be4738250.png the folder is ff01d10f8d and the file is 9be4738250.png.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `image_file` (`string`, required): File name of the generated image, the last segment of its URL including the extension. Example: 9be4738250.png.
- `image_folder` (`string`, required): First path segment of the generated image URL after the host. Example: ff01d10f8d.

Example input: `{"image_file":"<image_file>","image_folder":"<image_folder>"}`

### `dynapictures_media_asset_delete`

Delete Media Asset · Destructive

Permanently delete an image or folder from a workspace's media library.
Returns the deleted asset's fields.
Use dynapictures_media_assets_list to find asset IDs.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `asset_id` (`string`, required): ID of the asset to delete. Example: 5a12844966.
- `workspace_id` (`string`, required): ID of the workspace, from dynapictures_workspaces_list. Example: 8eb9e4869b.

Example input: `{"asset_id":"<asset_id>","workspace_id":"<workspace_id>"}`

### `dynapictures_webhook_unsubscribe`

Unsubscribe Webhook · Destructive

Remove a new-image webhook subscription.
Returns error false and a message.
Send the same target URL and template ID used in dynapictures_webhook_subscribe.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `target_url` (`string`, required): URL of your endpoint that receives the new-image notifications. Example: https://example.com/webhooks/dynapictures.
- `template_id` (`string`, required): ID of the design template whose new images trigger the webhook. Example: 000d61e4f7.

Example input: `{"target_url":"<target_url>","template_id":"<template_id>"}`

### `dynapictures_workspace_delete`

Delete Workspace · Destructive

Permanently delete a workspace with all its templates, media library files and generated images.
Returns the deleted workspace's id, name, dateCreated and dateUpdated.
This cannot be undone. Needs workspace admin permission.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `workspace_id` (`string`, required): ID of the workspace to delete, from dynapictures_workspaces_list. Example: 74b5b2c96a.

Example input: `{"workspace_id":"<workspace_id>"}`

## Related

Other Design connectors ([all 34](/agentkit/connectors/?category=design)):

- [Figma](/agentkit/connectors/figma/): Scalekit connector, OAuth, 54 tools
- [Miro](/agentkit/connectors/miro/): Scalekit connector, OAuth, 115 tools
- [Mural](/agentkit/connectors/mural/): Scalekit connector, OAuth, 61 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
