- MONITOR
- AUDIT
- REPORT
- HUMAN
Short answer
How can I track my Snowflake compute usage with AI?
Your AI uses the Snowflake MCP to pull a list of your warehouses and check current session details. You get immediate visibility into which warehouses are active and how they are being used.
Where your data lands.
What you get from your AI
The AI handles the data retrieval so you can focus on optimization.
MONITOR
Live warehouse status
The AI pulls a list of all available warehouses. You'll see exactly what's running in your account right now.
AUDIT
Session context check
Get details on the current session to see how compute is being applied. This helps you spot idle or heavy sessions.
REPORT
Usage summaries
Ask for a breakdown of specific warehouses. Your AI aggregates the data into a readable format.
HUMAN
Manual adjustments
The AI identifies usage patterns, but you still make the final call on resizing or suspending warehouses.
The workflow
What your AI does when the request arrives.
The AI translates your questions into specific Snowflake commands.
Identify warehouses
The AI scans your Snowflake account to find all available compute resources.
list_warehousesCheck session state
The AI looks at the current connection details to understand the active environment.
get_session_contextAnalyze usage
The AI compares the list of warehouses against your specific question to find the right data.
list_warehousesget_session_contextReport findings
The AI presents the warehouse status and session info in plain text for you to read.
list_warehouses
Try it
Copy these to start.
Use these prompts to begin monitoring your Snowflake environment.
Starting points
These are basic questions. You can swap in specific warehouse names to get more targeted answers.
Snowflake Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_FZdNhx3MFhQbRsBvKlZ0olbBDFO6A5aMdUPyNnlO/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Snowflake capabilities are ready to use.
{
"mcpServers": {
"snowflake-mcp": {
"url": "https://edge.vinkius.com/vk_preview_FZdNhx3MFhQbRsBvKlZ0olbBDFO6A5aMdUPyNnlO/mcp"
}
}
}List all my Snowflake warehouses.
Which warehouses are currently active?
Show me the context for my current Snowflake session.
Check the status of the PROD_WH warehouse.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Snowflake once, then ask.
Just enter your credentials once. Vinkius keeps your connection secure, and you can immediately start chatting with your Snowflake data in any compatible client.
Connect Snowflake to your AIFAQ
How this task behaves
- 01
Can the AI resize my Snowflake warehouses?
No. The AI can only read warehouse lists and session data. You must manually resize warehouses through the Snowflake UI or via SQL.
- 02
Can the AI delete my data or warehouses?
No. This MCP only has tools to list warehouses and get session context. It cannot perform any write or delete operations.
- 03
Do I need to write SQL to get these answers?
No. You just ask your AI in plain English, and it handles the tool calls for you.
- 04
Can I see real-time credit consumption?
The AI can see the status of warehouses through the available tools, but it cannot pull historical billing or credit usage logs.
- 05
Is my Snowflake password stored by the AI?
No. Vinkius manages the connection securely, and your credentials stay encrypted.
More questions about Snowflake? See everything the Snowflake Connector can do
Connect Snowflake to Claude, Cursor, ChatGPT & more
