qbash Connectors / Google News

Google News alerts for Python tasks.Run when matching articles arrive.

qbash checks Google News RSS for your search terms. New articles start a task, where your Python can filter the results or call a saved AI prompt.

Connect Google News free

MCP server

Build a Google News MCP server

Give ChatGPT, Claude and your other AI tools a Google News Task as a tool on one server, next to your other connectors and memory folders.

How to set it up

Connect Google News on the qbash Connectors page.
Save a Google News Task, then add it to an MCP server.
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 Google News task in Python

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

Summarise new stories about your market

Pass the articles from the Google News trigger to an inline prompt that writes a short digest with source links.

main.py
articles = qbash.inputs.get("articles", [])
if articles:
    digest = qbash.ai.run_prompt(
        slug="google-news-digest",
        variables={"articles": json.dumps(articles)},
    )
    qbash.output(digest)
else:
    qbash.output("No new articles arrived in this check.")

Trigger inputs

Polling trigger

A check with new matching articles starts one run and passes them together.

Article inputs

Each article includes title, link, source, snippet, and published_at. The payload also includes query and article_count.

Ways to use Google News

Morning coverage digest

Check your industry terms each morning, then summarise the new headlines with their source links.

Company mentions in Slack

Watch for new company mentions and send matching article links to the communications channel. Add a Slack connection for delivery.

Slack

qbash Tasks: AI applications in Python

A Task is a Python function that calls Google News, 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.