qbash Connectors / Snowflake

Snowflake MCP serverand Python AI tasks

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

Connect Snowflake free

MCP server

Build a Snowflake MCP server

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

How to set it up

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

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

Summarise seven days of trade volume by currency pair

The query totals trades and US dollar notional per pair for each day. An inline prompt turns the totals into a note on the busiest pairs and the largest day-to-day changes.

main.py
report = qbash.integrations.snowflake.execute_query(
    query="""SELECT trade_date, currency_pair, COUNT(*) AS trades,
                    SUM(notional_usd) AS notional_usd
             FROM fx_trades
             WHERE trade_date >= DATEADD(day, ?, CURRENT_DATE())
             GROUP BY trade_date, currency_pair
             ORDER BY trade_date, notional_usd DESC""",
    query_params=[-7], read_only=True,
)
rows = report["result"]
if rows:
    note = qbash.ai.run_prompt(
        slug="snowflake-fx-volume",
        variables={"volumes": json.dumps(rows)},
    )
    qbash.output(note)
else:
    qbash.output("No FX trades were recorded in the last seven days.")

Sample execute_query response

{
  "status": "success",
  "result": [
    {
      "TRADE_DATE": "2026-10-13",
      "CURRENCY_PAIR": "EUR/USD",
      "TRADES": 1764,
      "NOTIONAL_USD": "2291400000.00"
    },
    {
      "TRADE_DATE": "2026-10-13",
      "CURRENCY_PAIR": "USD/JPY",
      "TRADES": 1129,
      "NOTIONAL_USD": "1478250000.00"
    },
    {
      "TRADE_DATE": "2026-10-14",
      "CURRENCY_PAIR": "EUR/USD",
      "TRADES": 1842,
      "NOTIONAL_USD": "2384150000.00"
    },
    {
      "TRADE_DATE": "2026-10-14",
      "CURRENCY_PAIR": "USD/JPY",
      "TRADES": 1407,
      "NOTIONAL_USD": "1902600000.00"
    }
  ],
  "row_count": 4,
  "total_rows": 4,
  "truncated": false,
  "rows_affected": null,
  "query_id": "01bf6c2e-0001-4a7d-0000-3e5b00a2f19a"
}

What the Snowflake connector can do

Run one SQL statement in Snowflake and return its rows. It runs with the rights of the credential's role, so a role granted only SELECT keeps it to reads. Set read_only to refuse anything but SELECT, WITH, SHOW, DESCRIBE and EXPLAIN
Insert rows into a Snowflake table. Each row is a dict keyed by column name
List the databases the credential's role can see
List the schemas in a Snowflake database
List the tables and views in a Snowflake schema
Describe the columns of a Snowflake table or view
List the Snowflake warehouses the credential's role can see, with their size and state

See every Snowflake method in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls Snowflake, 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

Snowflake MCP questions

Does Snowflake have an official MCP server?

Yes. The Snowflake-managed MCP server, generally available since November 2025, exposes Cortex Analyst, Cortex Search and SQL execution as tools and signs in with Snowflake OAuth. The qbash server signs in with your key pair or token and shares one URL with your other connectors.