qbash Connectors / Massive

Massive MCP serverand Python AI tasks

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

MCP server

Build a Massive MCP server

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

How to set it up

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

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

Write a news digest for one ticker

Read the latest articles for a ticker and ask an inline prompt to group the coverage with links to each source.

main.py
report = qbash.integrations.massive.ticker_news(
    ticker="AAPL",
    order="desc",
    sort="published_utc",
    limit=20,
)
articles = report.get("results")
if isinstance(articles, list) and articles:
    digest = qbash.ai.run_prompt(
        slug="massive-news-digest",
        variables={"ticker": "AAPL", "articles": json.dumps(articles)},
    )
    qbash.output(digest)
else:
    qbash.output("No recent articles were returned for this ticker.")

Sample ticker_news response

{
  "status": "success",
  "results": [
    {
      "id": "news-1",
      "title": "Apple supplier reports higher quarterly orders",
      "publisher": {
        "name": "Example Wire"
      },
      "published_utc": "2026-09-30T13:00:00Z",
      "article_url": "https://example.com/apple-supplier-orders",
      "tickers": [
        "AAPL"
      ],
      "description": "A component supplier cited stronger demand for the coming quarter."
    }
  ],
  "count": 1,
  "next_url": null
}

What the Massive connector can do

OHLCV aggregate bars for a ticker over a date range. Multiplier + timespan (e.g. 5/minute, 1/day). `from`/`to` accept YYYY-MM-DD or unix-millis
Previous-day OHLCV bar for a ticker
Most recent NBBO quote (bid/ask) for a ticker. Requires a paid plan for real-time
Most recent trade for a ticker
Descriptive metadata for a ticker (name, market cap, description, branding, etc.)
Paginated reference list of tickers. Filter by exchange, type, market, CIK/CUSIP, or search
News articles index. Filter by ticker and publish-time range
Snapshot of all options contracts for an underlying asset, with greeks and last quote. Use strike_price_gte/lte and expiration_date_gte/lte to filter
Snapshot of one specific options contract (e.g. O:AAPL250620C00200000)
Reference list of historical and active option contracts
Current US market status (open/closed, after-hours, exchanges)
Reference list of exchanges Massive tracks
Daily OHLCV bars for the entire US equities market on a single date. One request covers the whole market for that date, typically several thousand rows

See every Massive method in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls Massive, 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

Massive MCP questions

Does Massive have an official MCP server?

Yes. Massive publishes an open-source MCP server, mcp_polygon on GitHub, that you run with your own API key. qbash runs the connection for you and can serve it on one URL with other connectors and Tasks.

Which Massive plan do I need?

Data access and delays follow your Massive plan, and real-time last quotes need a paid one. A Polygon.io key issued before the rename works for this connection.

Can the Massive MCP server place trades?

No. Massive is a data API, and the qbash Massive connector has no brokerage or order methods.

Guides that use Massive

Build a Massive task

Write it in Python with AI steps, and qbash hosts it with versions and run logs.

Build a task

Build a Massive MCP server

Pick the Massive tools to share and connect ChatGPT, Claude or Grok Bot.

Build an MCP server

Massive MCP serverand Python AI tasks