Connect AI agents to the Supadata MCP server

Vendor MCP

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.

Tools: 9
What they doRead · write · destructive: 7 · 2 · 07 read2 write0 destructive
Users sign in with: OAuth
OAuth app: Scalekit's or your own

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
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.
Scalekit credentials are available for Supadata, so you don't need to register an OAuth app.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'supadatamcp'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Supadata MCP:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'supadatamcp_supadata_check_crawl_status',
27
  toolInput: { id: 'YOUR_ID' },
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "supadatamcp"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Supadata MCP:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={"id":"YOUR_ID"},
27
    tool_name="supadatamcp_supadata_check_crawl_status",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

supadatamcp_supadata_check_crawl_statusCheck crawl job status and retrieve results.Read-only
Supadata Check Crawl Status
Check crawl job status and retrieve results. Returns status: scraping, completed, failed, or cancelled.
Inputs
idstringrequired
The job ID returned by supadata_crawl when the crawl job was created.
supadatamcp_supadata_check_extract_statusCheck extract job status and retrieve results.Read-only
Supadata Check Extract Status
Check extract job status and retrieve results. Returns status: queued, active, completed, or failed.
Inputs
idstringrequired
The job ID returned by supadata_extract when the extraction job was created.
supadatamcp_supadata_check_transcript_statusCheck transcript job status and retrieve results.Read-only
Supadata Check Transcript Status
Check transcript job status and retrieve results. Returns status: queued, active, completed, or failed.
Inputs
idstringrequired
The job ID returned by supadata_transcript for a large file transcription job.
supadatamcp_supadata_mapDiscover URLs on a websiteRead-only
Supadata Map Website
Discover URLs on a website
Inputs
urlstringrequired
The full URL of the website to map.
supadatamcp_supadata_metadataFetch metadata from a media URL (YouTube, TikTok, Instagram, Twitter).Read-only
Supadata Get Media Metadata
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.
Inputs
urlstringrequired
The full URL of the media content to fetch metadata for.
supadatamcp_supadata_scrapeScrape a single web page and return its content.Read-only
Supadata Scrape Page
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.
Inputs
urlstringrequired
The full URL of the web page to scrape.
langstring
Language code to filter or request content in (e.g. 'en', 'fr'). Optional.
noLinksboolean
When true, strips all hyperlinks from the scraped content. Optional, defaults to false.
supadatamcp_supadata_transcriptExtract transcript from a video or file URL.Read-only
Supadata Get Transcript
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.
Inputs
urlstringrequired
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).
chunkSizenumber
Maximum characters per timestamped segment (at least 50). Ignored when text is true.
langstring
Preferred transcript language as an ISO 639-1 code, e.g. "en". Falls back to the first available language.
modestring
"native" only fetches an existing transcript, "generate" always transcribes with AI, "auto" (default) tries native first and falls back to generate.one of nativeautogenerate
textboolean
true returns the transcript as plain text; false (default) returns timestamped segments.
supadatamcp_supadata_crawlCreate a crawl job to extract content from all pages on a website.Write
Supadata Crawl Website
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.
Inputs
urlstringrequired
Full URL to start crawling from, including https://.
limitnumber
Maximum number of pages to crawl (1-5000, default 100). Each page costs 1 credit.
supadatamcp_supadata_extractExtract structured data from a video URL using AI.Write
Supadata AI Extract from Video
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.
Inputs
urlstringrequired
The full URL of the video to extract structured data from.
promptstring
Natural language prompt describing what to extract from the video. Optional if schema is provided.
schemaobject
JSON Schema defining the structure of the extracted output. Optional if prompt is provided.

Setup

Install the SDK

Set your credentials

Create the Supadata MCP connection

Authorize a user and make your first call

Tools

Call it

Returns

Supadata Check Crawl Status

Inputs

Supadata Check Extract Status

Inputs

Supadata Check Transcript Status

Inputs

Supadata Map Website

Inputs

Supadata Get Media Metadata

Inputs

Supadata Scrape Page

Inputs

Supadata Get Transcript

Inputs

Supadata Crawl Website

Inputs

Supadata AI Extract from Video

Inputs

Other ways to connect Supadata

Related: other AI connectors