> **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 CaptureKit

The CaptureKit connector lets your AI agent act in each user's CaptureKit account. Each user connects their own CaptureKit API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 4 tools.

**Authentication:** API Key
**Categories:** Developer Tools, AI
**Tools:** 4: 4 read, 0 write, 0 destructive
**Users sign in with:** API key
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=CAPTUREKIT)

## 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 CaptureKit connection

   In **AgentKit > Connections**, create a CaptureKit 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 = 'capturekit'
   const identifier = 'user_123'

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

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

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

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their CaptureKit 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: 'capturekit_content_get',
  toolInput: {
    url: '<url>',
  },
  connector: 'capturekit',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="capturekit_content_get",
    tool_input={
        "url": "<url>",
    },
    connection_name="capturekit",
    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.

### `capturekit_content_get`

Get Page Content · Read-only

Load a webpage in a browser and extract its content, optionally as cleaned Markdown, raw HTML and the site's sitemap.
Returns the page's title, metadata, links and text, plus HTML, Markdown or sitemap when requested.
Use use_defuddle true for the main article content only.

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

Inputs:

- `url` (`string`, required): The URL of the webpage to capture. Example: https://example.com/pricing.
- `block_resources` (`string`, optional): Comma-separated list of resource types to block (e.g., “image,stylesheet,font”). Types: document, stylesheet, image, media, font, script, texttrack, xhr, fetch, eventsource, websocket, manifest, other. Example: image,font.
- `block_urls` (`string`, optional): Comma-separated list of URL patterns to block (e.g., “analytics,tracking,advertisement”). You can specify URLs, domains, or simple patterns like “.example.com/”. Example: analytics,tracking.
- `cache` (`boolean`, optional): Cache the response. Example: true.
- `cache_ttl` (`integer`, optional): Cache the response for a custom TTL (in seconds). Example: 3600.
- `delay` (`integer`, optional): Delay in seconds before capturing the screenshot. Example: 2.
- `include_html` (`boolean`, optional): Include the raw HTML of the webpage in the response. Example: true.
- `include_markdown` (`boolean`, optional): Include the Markdown of the webpage in the response. Example: true.
- `include_sitemap` (`boolean`, optional): Include the sitemap of the website in the response. Example: true.
- `proxy` (`string`, optional): Specify a proxy server to route your request through. Supports HTTP, HTTPS, and SOCKS5 proxies. Format: http://username:password@proxy.com:PORT. Useful for bypassing geo-restrictions and rotating IPs. Example: http://user:pass@proxy.example.com:8080.
- `remove_ads` (`boolean`, optional): Automatically remove ads before capturing. Example: true.
- `remove_cookie_banners` (`boolean`, optional): Automatically remove cookie banners before capturing. Example: true.
- `remove_selectors` (`string`, optional): A comma-separated list of elements to hide before capturing (e.g., ads, popups). Example: .newsletter-popup,#chat-widget.
- `use_defuddle` (`boolean`, optional): Use Defuddle to clean and extract the main content from web pages. This popular library removes unnecessary elements like comments, sidebars, headers, footers, and other non-essential elements, leaving only the primary content. When enabled, the HTML response will be processed through Defuddle before being returned. Example: true.
- `wait_for_selector` (`string`, optional): Wait for a specific element to appear before taking the screenshot. Example: #main-content.
- `wait_until` (`string`, optional): Define when to capture. Example: networkidle2. One of: `domcontentloaded`, `load`, `networkidle0`, `networkidle2`.

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

### `capturekit_page_analyze`

Analyze Page with AI · Read-only

Load a webpage and have AI analyze it, optionally guided by your own prompt and extra response fields.
Returns structured insights about the page's content, design and technology, plus any custom fields.
Use capturekit_content_get for the raw text or Markdown.

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

Inputs:

- `url` (`string`, required): The URL of the webpage to capture. Example: https://example.com/pricing.
- `cache` (`boolean`, optional): Cache the response. Example: true.
- `cache_ttl` (`integer`, optional): Cache the response for a custom TTL (in seconds). Example: 3600.
- `custom_prompt` (`string`, optional): Add your own instructions to guide the AI’s analysis. Example: List the pricing tiers and their monthly prices.
- `custom_response` (`string`, optional): JSON-stringified object of extra fields the AI should fill in, mapping each field name to what it should hold. Example: {"sentiment": "sentiment", "language": "language"}
- `proxy` (`string`, optional): Specify a proxy server to route your request through. Supports HTTP, HTTPS, and SOCKS5 proxies. Format: http://username:password@proxy.com:PORT. Useful for bypassing geo-restrictions and rotating IPs. Example: http://user:pass@proxy.example.com:8080.

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

### `capturekit_usage_get`

Get Usage · Read-only

Get the account's live quota and credit usage.
Returns remaining, total_used, renewal_date, subscription and credits balances, packs, rate limits and the API key's details.
It costs no credits.

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

Inputs: none.

Example input: `{}`

### `capturekit_website_crawl`

Crawl Website Page · Read-only

Fetch a web page through CaptureKit's crawler.
Returns the page data, or its HTML source when return_page_source is true.
Use capturekit_content_get for rendered content and Markdown.

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

Inputs:

- `query` (`string`, required): A website URL with either the http or https protocol. Example: https://example.com.
- `allow_redirects` (`boolean`, optional): If set to false, do not follow redirects. Example: true.
- `return_page_source` (`boolean`, optional): If set to true, the response will be the HTML source of the page. Example: true.

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

## Related

Other Developer Tools connectors ([all 200](/agentkit/connectors/?category=developer-tools)):

- [GitHub](/agentkit/connectors/github/): Scalekit connector, OAuth, 217 tools
- [Datadog](/agentkit/connectors/datadog/): Scalekit connector, API key, 105 tools
- [Linear](/agentkit/connectors/linear/): Scalekit connector, OAuth, 64 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 |
