Skip to content
Try for free

Connect Snowflake to Cursor

  • Is the new field arriving?

Check the SQL and tracking code you're editing in Cursor against what actually lands in Snowflake. Lemonado connects them in about 2 minutes, no API keys needed.

Try free with $150 in creditsJump to the steps
MCPhttps://mcp.lemonado.io/mcp

Why connect Snowflake to Cursor?

A renamed event or a new checkout field shows up in Snowflake days later, as a broken dashboard. Cursor's agent sees the change while you make it. With Lemonado it can query Snowflake right away, so you see what your change does to the warehouse before you ship it.

  • All your Snowflake data

    Tables and views your role can read, ready to ask about.

  • Always today's numbers

    Column names, types and descriptions, synced from Snowflake automatically, so answers use today's numbers.

  • Connect all your tools

    Questions like "What does a paying customer cost?" use Snowflake and BigQuery, GA4 at once.

How to connect Snowflake to Cursor

Before you start

  • A Snowflake account you can sign in to
  • Cursor installed
  • A Lemonado account (the free trial works)
  1. 1

    Connect Snowflake in Lemonado

    In Lemonado, open Connectors, find Snowflake and sign in. Create a read-only role that can use one warehouse and the schemas marketing should see, and connect with that. Keep raw PII schemas out of the grant.

  2. 2

    Turn on external access

    In the company's settings, open External tools, turn the connection on, choose which sources it can reach and copy the server URL.

    text
    https://mcp.lemonado.io/mcp
  3. 3

    Open your MCP config

    Open ~/.cursor/mcp.json for every project, or .cursor/mcp.json for this project only. Create the file if it doesn't exist.

  4. 4

    Add Lemonado

    Merge this into the file and save.

    json
    {
  "mcpServers": {
    "lemonado": {
      "url": "https://mcp.lemonado.io/mcp"
    }
  }
}
  5. 5

    Sign in

    Cursor asks you to sign in to Lemonado. Approve access, then ask the agent about your data.

  6. 6

    Ask Cursor about Snowflake

    Try "I added discount_code to the checkout payload in lib/checkout.ts last week. Check whether it's arriving in Snowflake's raw orders table, and how often it's filled." Or ask: "Which column does the dashboard use?" or "Will this query be slow?"

Good to know

  • Editing the file directly avoids relying on menu labels that change between Cursor versions.

What can Cursor do with Snowflake?

Cursor's agent reads your Snowflake data while it edits: it fills components with real data, checks tracking code and writes the analysis next to your code.

Cursor logoCursor

I added discount_code to the checkout payload in lib/checkout.ts last week. Check whether it's arriving in Snowflake's raw orders table, and how often it's filled.

It arrives, but only on 12% of orders since the release. Orders paid with Apple Pay skip the code in lib/checkout.ts that adds it.

Source: Snowflake + your code

Connect Snowflake to another AI app.

Other integrations for Cursor

All Cursor integrations

Reading this as an AI agent?

Everything an agent needs to set this up, in plain text. Paste this page's link into Cursor and ask it to connect you, or copy the block.

For agents · markdown
# Connect Snowflake to Cursor (Lemonado MCP)

- Server URL: https://mcp.lemonado.io/mcp
- Transport: Streamable HTTP
- Auth: OAuth; the user signs in to Lemonado in the browser. No API keys.
- In Lemonado: connect the Snowflake role and warehouse. Create a read-only role that can use one warehouse and the schemas marketing should see, and connect with that. Keep raw PII schemas out of the grant.
- In Cursor: ~/.cursor/mcp.json

```json
{
  "mcpServers": {
    "lemonado": {
      "url": "https://mcp.lemonado.io/mcp"
    }
  }
}
```

First question to try: "I added discount_code to the checkout payload in lib/checkout.ts last week. Check whether it's arriving in Snowflake's raw orders table, and how often it's filled."

More: https://lemonado.io/integrations/snowflake · https://lemonado.io/llms.txt
FAQ

Frequently Asked Questions

No. Lemonado reads Snowflake with the role you connect, and that should be a read-only role. Changes to models and tracking happen in your code, and your normal deploy runs them.

Yes. Snowflake's managed MCP server is hosted, so Cursor can use it too. It covers Snowflake only. Lemonado covers Snowflake plus your ad platforms, GA4 and the rest of your stack in one connection, so Cursor can answer questions across them.

Open Cursor's settings and find lemonado in the MCP list. A red dot or a sign-in prompt means the login expired. Restart Cursor after editing mcp.json. In Lemonado, check that Snowflake is connected and External tools is on for the company. If a table is missing, the role can't see it. Grant USAGE on its database and schema and SELECT on the table, then ask again.

Yes, if both are connected in Lemonado. One connection reaches every source you allow, so you can ask things like "Compare the purchases Google Ads reported last week with orders in Snowflake that have a gclid."

MCP is included in Lemonado's paid plans and in the free trial, so you can try it before you pay.

See plans and pricing

Still have a question?

Shoot us an email at hello@lemonado.io.

Try for free

Stop fighting with data. Start feeding your AI.

Connect your data to AI and free your team from reporting and busywork.

Try Lemonado free