qbash Connectors / Supermetrics

Supermetrics MCP serverand Python AI tasks

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

Connect Supermetrics free

MCP server

Build a Supermetrics MCP server

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

How to set it up

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

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

Review a week of Google Ads campaigns

Query seven days of campaign metrics through Supermetrics, then ask an inline prompt to flag campaigns whose cost per conversion moved.

main.py
report = qbash.integrations.supermetrics.data_query(
    ds_id="AW",
    ds_accounts=["1234567890"],
    fields=["Date", "Campaignname", "Impressions", "Clicks", "Cost", "Conversions"],
    date_range_type="last_7_days",
    max_rows=500,
)
rows = report.get("rows", [])
if rows:
    review = qbash.ai.run_prompt(
        slug="supermetrics-campaign-review",
        variables={"rows": json.dumps(rows)},
    )
    qbash.output(review)
else:
    qbash.output({
        "message": "No rows returned yet.",
        "query_status": report.get("query_status"),
        "schedule_id": report.get("schedule_id"),
    })

Sample data_query response

{
  "status": "success",
  "query_status": "completed",
  "status_code": "SUCCESS",
  "schedule_id": "abc123def456",
  "fields": [
    "Date",
    "Campaignname",
    "Impressions",
    "Clicks",
    "Cost",
    "Conversions"
  ],
  "rows": [
    {
      "Date": "2026-10-14",
      "Campaignname": "Brand - Search",
      "Impressions": 5210,
      "Clicks": 388,
      "Cost": 412.55,
      "Conversions": 31
    },
    {
      "Date": "2026-10-14",
      "Campaignname": "Competitors - Search",
      "Impressions": 2980,
      "Clicks": 141,
      "Cost": 530.1,
      "Conversions": 4
    }
  ],
  "row_count": 2,
  "total_rows": 2,
  "offset_start": 0,
  "offset_end": 9999,
  "next_offset_start": null,
  "row_limit_reached": false,
  "start_date": "2026-10-14",
  "end_date": "2026-10-20",
  "data_sampled": false,
  "cache_used": false,
  "cache_time": null
}

What the Supermetrics connector can do

List Supermetrics data sources and which ones the team has connected, or return one source's report types and settings
List the accounts the team's Supermetrics logins can query for a data source
List the metrics and dimensions a Supermetrics data source offers
Run a Supermetrics report query and return rows keyed by field ID
Wait for a Supermetrics query by schedule ID and return a page of its rows

See every Supermetrics method in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls Supermetrics, 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

Supermetrics MCP questions

Does Supermetrics have an official MCP server?

Yes. Supermetrics runs its own hosted MCP server at mcp.supermetrics.com. The qbash server calls the Supermetrics REST API with your API key and can share one MCP URL with tools from your other connectors. Python tasks can run the same queries on a schedule.