qbash Connectors / Supadata

Supadata MCP serverand Python AI tasks

qbash hosts a Supadata MCP server you can use in Claude, ChatGPT, Codex, Cursor, Grok Bot and Muse.

Developers use qbash Tasks to write cloud-hosted Python functions that pair Supadata with models such as Claude and GPT.

Connect Supadata free

MCP server

Build a Supadata MCP server

Give ChatGPT, Claude and your other AI tools access to Supadata through one server. You pick which Supadata tools it shares, and you can add other connectors, memory folders and Tasks to the same server.

How to set it up

Connect Supadata on the qbash Connectors page.
Create an MCP server and add the Supadata tools you want to share.
Paste the server URL into your client. It connects with OAuth or an access token.

Connect a client Package an MCP server

Python AI task

Write a Supadata task in Python

A qbash Task is a hosted Python function that calls Supadata and AI models.

Review a product’s public pricing page

Fetch a web page and ask an inline prompt to extract plan names, prices, and stated limits.

main.py
page = qbash.integrations.supadata.scrape_web(
    url="https://example.com/pricing",
)
content = page.get("content") if isinstance(page, dict) else page
if isinstance(content, str) and content.strip():
    review = qbash.ai.run_prompt(
        slug="pricing-page-review",
        variables={"page": content[:20000]},
    )
    qbash.output(review)
else:
    qbash.output("No text content was returned for this page.")

Sample scrape_web response

{
  "content": "# Pricing\nStarter: $20 per month, includes 5 seats.\nBusiness: Contact sales."
}

What the Supadata connector can do

Scrape content from a single web page
Map a website to discover the URLs Supadata finds on it
Extract the transcript from a YouTube video
Get videos from a YouTube channel

See every Supadata method in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls Supadata, your other connectors and models such as Claude, GPT, Gemini and Grok. qbash hosts and runs it.

Run Tasks on a schedule or from your team's tools

+ more

Deterministic where it counts Write the logic in Python and call a model only for the steps that need judgement, so the rest runs the same way every time.
Version controlled Every save is a revision you can compare and roll back.
Logged Each run records its inputs, output, errors and what started it.
Shared credentials Connections belong to your organization, so a Task keeps working when its author is away.

qbash Tasks Python AI SDK

Supadata MCP questions

Does Supadata have its own MCP server?

Yes. Supadata publishes one, listed in Docker’s MCP catalog, that you run with your API key. qbash runs Supadata as a hosted URL that can carry your other connectors too, and Python tasks reach the same methods.

Can the assistant map a whole website?

map_website is a Python method and is left out of the Supadata tools qbash serves over MCP. Write a task that maps the site and scrapes the pages, then add that task to the same server as one tool.