> **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 Claid AI

The Claid AI connector lets your AI agent act in each user's Claid AI account. Each user connects their own Claid AI 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, AI
**Tools:** 17: 8 read, 8 write, 1 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=CLAID)

## 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 Claid AI connection

   In **AgentKit > Connections**, create a Claid AI 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 = 'claid'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Claid AI:', 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: 'claid_storage_types_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 = "claid"
   identifier = "user_123"

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

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

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Claid AI 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: 'claid_ai_edit_get',
  toolInput: {
    task_id: 4521,
  },
  connector: 'claid',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="claid_ai_edit_get",
    tool_input={
        "task_id": 4521,
    },
    connection_name="claid",
    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.

### `claid_ai_edit_get`

Get AI Image Edit · Read-only

Get the status and result of an AI image edit.
Returns the task status and, when done, the output image URLs.
Poll it after ai_edit_create.

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

Inputs:

- `task_id` (`integer`, required): ID of the AI edit task, from the id in the create tool's response. Example: 4521.

Example input: `{"task_id":4521}`

### `claid_fashion_models_get`

Get AI Fashion Model Photos · Read-only

Get the status and result of an AI fashion models task.
Returns the task status and, when done, the generated image URLs.
Poll it after fashion_models_create.

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

Inputs:

- `task_id` (`integer`, required): ID of the AI fashion models task, from the id in the create tool's response. Example: 4521.

Example input: `{"task_id":4521}`

### `claid_image_edit_async_get`

Get Async Image Edit · Read-only

Get the status and result of an asynchronous image edit.
Returns the task status (ACCEPTED, PROCESSING, DONE or ERROR) and, when done, the output image details and URL.
Poll it after image_edit_async.

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

Inputs:

- `task_id` (`integer`, required): ID of the async image edit task, from the id in the create tool's response. Example: 4521.

Example input: `{"task_id":4521}`

### `claid_image_edit_batch_get`

Get Batch Image Edit · Read-only

Get the status and results of a batch image edit.
Returns the task status and, per processed image, its input, output and any error.
Poll it after image_edit_batch.

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

Inputs:

- `task_id` (`integer`, required): ID of the batch image edit task, from the id in the create tool's response. Example: 4521.

Example input: `{"task_id":4521}`

### `claid_storage_get`

Get Storage · Read-only

Get one connected storage.
Returns its name, type and settings (without secrets).
Use storages_list to find storage IDs.

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

Inputs:

- `storage_id` (`integer`, required): ID of the storage, from storages_list. Example: 12.

Example input: `{"storage_id":12}`

### `claid_storage_types_list`

List Storage Types · Read-only

List the storage types Claid can connect to (such as AWS S3, Google Cloud Storage and web folders).
Returns each type's name and required settings.
Storages are connected in the Claid dashboard.

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

Inputs: none.

Example input: `{}`

### `claid_storages_list`

List Storages · Read-only

List the external storages connected to your Claid account.
Returns each storage's id, name, type and settings (without secrets).
Use a storage name in storage:// URIs for input and output.

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

Inputs: none.

Example input: `{}`

### `claid_video_get`

Get Video Generation · Read-only

Get the status and result of an image-to-video task.
Returns the task status and, when done, the video URL.
Poll it after video_generate.

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

Inputs:

- `task_id` (`integer`, required): ID of the video generation task, from the id in the create tool's response. Example: 4521.

Example input: `{"task_id":4521}`

### `claid_ai_edit_create`

Edit Image with AI Instructions · Write

Edit an image from a natural language instruction, such as add a duck or change the background to a beach.
Returns a task id and status at once. Uses credits.
Poll ai_edit_get for the result.

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

Inputs:

- `input` (`string`, required): The image to edit: a public image URL or a storage:// URI. Example: https://picsum.photos/500.
- `options` (`object`, required): AI edit options; prompt (the instruction) is required. See https://docs.claid.ai/image-ai-edit-api/image-ai-edit-options for the other options. Example: {"prompt": "add a duck"}
- `output` (`object`, optional): Output settings: format (an object such as {"type": "jpeg", "quality": 90} or a string such as png), and optionally destination, a storage:// URI to save the result in a connected storage. Omit to get a temporary URL in the response. Example: {"format": {"type": "jpeg", "quality": 90}}

Example input: `{"input":"<input>","options":{"prompt":"add a duck"}}`

### `claid_fashion_models_create`

Generate AI Fashion Model Photos · Write

Generate photos of AI fashion models wearing your clothing items, with an optional model description, pose and background.
Returns a task id and status at once. Uses credits.
Poll fashion_models_get for the result.

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

Inputs:

- `input` (`object`, required): Input images: clothing (required, a list of clothing image URLs), plus optional model and background references. See https://docs.claid.ai/ai-fashion-models-api/ai-fashion-models-i-o. Example: {"clothing": ["https://images.claid.ai/photoshoot-templates/assets/images/b63641ea19dd4dac8fdc02a6195873f0.jpeg"]}
- `options` (`object`, optional): Generation options such as pose, model description, background and number of images. See https://docs.claid.ai/ai-fashion-models-api/ai-fashion-models-options. Example: {"pose": "full body, front view, neutral stance, arms relaxed"}
- `output` (`object`, optional): Output settings: format (an object such as {"type": "jpeg", "quality": 90} or a string such as png), and optionally destination, a storage:// URI to save the result in a connected storage. Omit to get a temporary URL in the response. Example: {"format": {"type": "jpeg", "quality": 90}}

Example input: `{"input":{"clothing":["https://images.claid.ai/photoshoot-templates/assets/images/b63641ea19dd4dac8fdc02a6195873f0.jpeg"]}}`

### `claid_image_edit`

Edit Image · Write

Edit one image synchronously: resize, upscale, restore, remove or replace the background, adjust colors, pad, blur faces and more, by combining operations.
Returns the input and output image details, including a temporary output URL (tmp_url) unless a storage destination is set. Uses credits.
Use image_edit_async for large images and image_edit_batch for folders.

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

Inputs:

- `input` (`string`, required): The image to edit: a public image URL or a storage:// URI of a connected storage. Example: https://claid.ai/assets/cms/shoe_example_05fb154a3a/shoe_example_05fb154a3a.png.
- `operations` (`object`, required): Edits to apply, grouped by operation type: restorations (upscale, decompress, polish), resizing (width, height, fit), adjustments (hdr, exposure, saturation, contrast, sharpness), background (remove, color, blur), padding and privacy (blur_car_plate). See https://docs.claid.ai/image-editing-api/image-operations. Example: {"resizing": {"width": 1000}, "background": {"remove": true, "color": "#ffffff"}, "restorations": {"upscale": "smart_enhance"}}
- `output` (`object`, optional): Output settings: format (an object such as {"type": "jpeg", "quality": 90} or a string such as png), and optionally destination, a storage:// URI to save the result in a connected storage. Omit to get a temporary URL in the response. Example: {"format": {"type": "jpeg", "quality": 90}}

Example input: `{"input":"<input>","operations":{}}`

### `claid_image_edit_async`

Edit Image Asynchronously · Write

Start editing one image asynchronously, with the same operations as image_edit.
Returns a task id and status at once; a webhook (configured in the Claid dashboard) or image_edit_async_get gives the result. Uses credits.
Use it for large images or slow operations.

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

Inputs:

- `input` (`string`, required): The image to edit: a public image URL or a storage:// URI of a connected storage. Example: https://claid.ai/assets/cms/shoe_example_05fb154a3a/shoe_example_05fb154a3a.png.
- `operations` (`object`, required): Edits to apply, grouped by operation type (restorations, resizing, adjustments, background, padding, privacy). See https://docs.claid.ai/image-editing-api/image-operations. Example: {"resizing": {"width": 1000}, "background": {"remove": true, "color": "#ffffff"}, "restorations": {"upscale": "smart_enhance"}}
- `output` (`object`, optional): Output settings: format (an object such as {"type": "jpeg", "quality": 90} or a string such as png), and optionally destination, a storage:// URI to save the result in a connected storage. Omit to get a temporary URL in the response. Example: {"format": {"type": "jpeg", "quality": 90}}

Example input: `{"input":"<input>","operations":{}}`

### `claid_image_edit_batch`

Edit Images in Batch · Write

Edit every image in a storage folder with the same operations, saving results to another storage folder.
Returns a task id and status at once. Uses credits per image.
Input and output must be storage:// folder URIs from a storage connected in Claid (see storages_list).

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

Inputs:

- `input` (`string`, required): Folder of images to edit, as a storage:// URI ending in /. Example: storage://storage_1/input_folder/.
- `operations` (`object`, required): Edits to apply to each image, grouped by operation type (restorations, resizing, adjustments, background, padding, privacy). Example: {"resizing": {"width": 1000}, "background": {"remove": true, "color": "#ffffff"}, "restorations": {"upscale": "smart_enhance"}}
- `output` (`string`, required): Folder to write the edited images to, as a storage:// URI ending in /. Example: storage://storage_1/output_folder/.

Example input: `{"input":"<input>","operations":{},"output":"<output>"}`

### `claid_image_generate`

Generate Image · Write

Generate images from a text prompt.
Returns the generated images' details and temporary URLs. Uses credits.
Use scene_create to place a product photo into a generated scene.

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

Inputs:

- `input` (`string`, required): Text prompt describing the image to generate. Example: A delicious ceviche cheesecake slice.
- `options` (`object`, optional): Generation options such as number_of_images (1-4) and guidance_scale. See https://docs.claid.ai/image-generation-api/image-generation-options. Example: {"number_of_images": 2, "guidance_scale": 5}
- `output` (`object`, optional): Output settings: format (an object such as {"type": "jpeg", "quality": 90} or a string such as png), and optionally destination, a storage:// URI to save the result in a connected storage. Omit to get a temporary URL in the response. Example: {"format": {"type": "jpeg", "quality": 90}}

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

### `claid_scene_create`

Create AI Background Scene · Write

Place a product image into an AI-generated background scene described by a prompt or a template image.
Returns the generated images' details and URLs. Uses credits.
Use image_generate for images without a product.

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

Inputs:

- `object` (`object`, required): The product: image_url (required, ideally with a transparent background), plus optional rotation_degree, scale and position (x, y from 0 to 1). Example: {"image_url": "https://images.claid.ai/photoshoot-templates/docs/product.png", "scale": 0.55, "position": {"x": 0.35, "y": 0.5}}
- `scene` (`object`, required): The background: prompt describing it, and optionally template_url, template_mode (such as transform) and view (such as front). See https://docs.claid.ai/ai-background-api/ai-background-options/scene. Example: {"prompt": "marble countertop, marble wall background, bokeh, professional product photography", "view": "front"}
- `output` (`object`, optional): Output settings: number_of_images and format (png, jpeg or webp), and optionally a storage destination. Example: {"number_of_images": 1, "format": "png"}

Example input: `{"object":{},"scene":{"prompt":"marble countertop, marble wall background, bokeh, professional product photography","view":"front"}}`

### `claid_video_generate`

Generate Video from Image · Write

Generate a short video from an image, with an optional or auto-generated prompt.
Returns a task id and status at once. Uses credits.
Poll video_get for the result.

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

Inputs:

- `input` (`string`, required): Source image: a public image URL or a storage:// URI. Example: storage://storage-name/input-path/input.png.
- `options` (`object`, optional): Video options such as prompt (an object with text, or generate true to write one automatically) and duration in seconds. See https://docs.claid.ai/image-to-video-api/image-to-video-options. Example: {"prompt": {"generate": true}, "duration": 5}
- `output` (`string`, optional): Where to save the video, as a storage:// folder URI. Omit to get a temporary URL. Example: storage://storage-name/output-path/.

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

### `claid_storage_delete`

Delete Storage · Destructive

Disconnect a storage from your Claid account.
Returns an empty response on success.
Files in the storage are not deleted.

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

Inputs:

- `storage_id` (`integer`, required): ID of the storage, from storages_list. Example: 12.

Example input: `{"storage_id":12}`

## 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 |
