> **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 the Supadata MCP server

The Supadata MCP connector routes your AI agent's tool calls to Supadata's own MCP server through Scalekit. Each user signs in to Supadata once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 9 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** AI, Analytics, Search, Transcription
**Tools:** 9: 7 read, 2 write, 0 destructive
**Users sign in with:** OAuth
**OAuth app:** Scalekit's or your own
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=SUPADATAMCP)

## 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 Supadata MCP connection

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

   Scalekit credentials are available for Supadata, so you don't need to register an OAuth app.

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 = 'supadatamcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Supadata MCP:', 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: 'supadatamcp_supadata_check_crawl_status',
     toolInput: { id: 'YOUR_ID' },
   })
   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 = "supadatamcp"
   identifier = "user_123"

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

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

   ```bash
   python quickstart.py
   ```

   Each user signs in once. 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: 'supadatamcp_supadata_check_crawl_status',
  toolInput: {
    id: '<id>',
  },
  connector: 'supadatamcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="supadatamcp_supadata_check_crawl_status",
    tool_input={
        "id": "<id>",
    },
    connection_name="supadatamcp",
    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.

### `supadatamcp_supadata_check_crawl_status`

Supadata Check Crawl Status · Read-only

Check crawl job status and retrieve results. Returns status: scraping, completed, failed, or cancelled.

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

Inputs:

- `id` (`string`, required): The job ID returned by supadata_crawl when the crawl job was created.

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

### `supadatamcp_supadata_check_extract_status`

Supadata Check Extract Status · Read-only

Check extract job status and retrieve results. Returns status: queued, active, completed, or failed.

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

Inputs:

- `id` (`string`, required): The job ID returned by supadata_extract when the extraction job was created.

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

### `supadatamcp_supadata_check_transcript_status`

Supadata Check Transcript Status · Read-only

Check transcript job status and retrieve results. Returns status: queued, active, completed, or failed.

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

Inputs:

- `id` (`string`, required): The job ID returned by supadata_transcript for a large file transcription job.

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

### `supadatamcp_supadata_map`

Supadata Map Website · Read-only

Discover URLs on a website

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

Inputs:

- `url` (`string`, required): The full URL of the website to map.

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

### `supadatamcp_supadata_metadata`

Supadata Get Media Metadata · Read-only

Fetch metadata from a media URL (YouTube, TikTok, Instagram, Twitter). Returns platform info, title, description, author details, engagement stats, media details, tags, and creation date.

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

Inputs:

- `url` (`string`, required): The full URL of the media content to fetch metadata for.

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

### `supadatamcp_supadata_scrape`

Supadata Scrape Page · Read-only

Scrape a single web page and return its content. Fetches and extracts the text content from the specified URL, with optional link removal and language filtering.

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

Inputs:

- `url` (`string`, required): The full URL of the web page to scrape.
- `lang` (`string`, optional): Language code to filter or request content in (e.g. 'en', 'fr'). Optional.
- `noLinks` (`boolean`, optional): When true, strips all hyperlinks from the scraped content. Optional, defaults to false.

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

### `supadatamcp_supadata_transcript`

Supadata Get Transcript · Read-only

Extract transcript from a video or file URL. For large files, returns a jobId instead of the transcript directly - use supadata_check_transcript_status with that jobId to poll for results.

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

Inputs:

- `url` (`string`, required): URL of a single video or post on YouTube, TikTok, Instagram, X (Twitter) or Facebook, or a direct link to an audio or video file. Not for ordinary web pages (use supadata_scrape).
- `chunkSize` (`number`, optional): Maximum characters per timestamped segment (at least 50). Ignored when text is true.
- `lang` (`string`, optional): Preferred transcript language as an ISO 639-1 code, e.g. "en". Falls back to the first available language.
- `mode` (`string`, optional): "native" only fetches an existing transcript, "generate" always transcribes with AI, "auto" (default) tries native first and falls back to generate. One of: `native`, `auto`, `generate`.
- `text` (`boolean`, optional): true returns the transcript as plain text; false (default) returns timestamped segments.

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

### `supadatamcp_supadata_crawl`

Supadata Crawl Website · Write

Create a crawl job to extract content from all pages on a website. Returns a jobId - use supadata_check_crawl_status with that jobId to poll for results.

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

Inputs:

- `url` (`string`, required): Full URL to start crawling from, including https://.
- `limit` (`number`, optional): Maximum number of pages to crawl (1-5000, default 100). Each page costs 1 credit.

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

### `supadatamcp_supadata_extract`

Supadata AI Extract from Video · Write

Extract structured data from a video URL using AI. Provide a prompt for what to extract, a JSON Schema for the output format, or both. Returns a jobId for async processing.

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

Inputs:

- `url` (`string`, required): The full URL of the video to extract structured data from.
- `prompt` (`string`, optional): Natural language prompt describing what to extract from the video. Optional if schema is provided.
- `schema` (`object`, optional): JSON Schema defining the structure of the extracted output. Optional if prompt is provided.

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

## Related

Other ways to connect Supadata:

- [API key](/agentkit/connectors/supadata/): Scalekit connector, API key, 21 tools

Other AI connectors ([all 155](/agentkit/connectors/?category=ai)):

- [Chorus](/agentkit/connectors/chorus/): Scalekit connector, Username and password, 9 tools
- [Gong](/agentkit/connectors/gong/): Scalekit connector, OAuth, 69 tools
- [Jiminny](/agentkit/connectors/jiminny/): Scalekit connector, Access token, 27 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 |
