qbash Connectors / Browserless

Browserless MCP serverand Python AI tasks

qbash hosts a Browserless 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 Browserless with models such as Claude and GPT.

Connect Browserless free

MCP server

Build a Browserless MCP server

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

How to set it up

Connect Browserless on the qbash Connectors page.
Create an MCP server and add the Browserless 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 Browserless task in Python

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

Turn a page’s controls into a test plan

Inspect a page’s interactive elements, then ask an inline prompt to draft test steps with the most stable selector for each.

main.py
page = qbash.integrations.browserless.inspect(
    url="https://example.com/pricing",
    includeHidden=False,
    timeoutMs=30000,
)
elements = page.get("elements", [])
if elements:
    plan = qbash.ai.run_prompt(
        slug="browserless-test-plan",
        variables={"url": page.get("url"), "elements": json.dumps(elements)},
    )
    qbash.output({"plan": plan, "truncated": page.get("truncated")})
else:
    qbash.output("The page has no interactive elements to test.")

Sample inspect response

{
  "url": "https://example.com/pricing",
  "title": "Pricing",
  "elements": [
    {
      "tag": "a",
      "role": "link",
      "text": "Start free trial",
      "href": "https://example.com/signup",
      "visible": true
    },
    {
      "tag": "button",
      "testId": "billing-toggle",
      "text": "Annual",
      "visible": true
    },
    {
      "tag": "input",
      "type": "email",
      "name": "email",
      "placeholder": "Work email",
      "label": "Email",
      "visible": true
    }
  ],
  "count": 3,
  "truncated": false
}

What the Browserless connector can do

List the interactive elements on a page with the selectors that find them. Call this before writing automation for a site you have not seen
Run browser automation and return what it observed. Assertions are code that throws; a thrown error comes back as ok=false with the message
Return a page's rendered HTML. Prefer `inspect` unless you need the raw markup
Capture a page as a PNG, returned base64-encoded

See every Browserless method in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls Browserless, 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

Browserless MCP questions

Does Browserless have an official MCP server?

Yes. Browserless runs a hosted MCP server at mcp.browserless.io. The qbash server uses your Browserless API token and can share one MCP URL with your other connectors, and Python tasks call the same four methods.

Who pays for the browser time?

Your Browserless account. Every call runs under your API token, and Browserless bills by connection time. qbash stops a call after 60 seconds by default, and timeoutMs raises that to at most 180 seconds.