Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.gumloop.com/llms.txt

Use this file to discover all available pages before exploring further.

Snowflake is a cloud data platform for analytics and data warehousing. The Snowflake MCP server lets you run SQL queries and inspect table schemas using natural language.

​
What Can It Do?

  • Run SQL queries and return structured results
  • Describe table schemas to understand your data
  • Bulk load data into tables via staging
  • Tag queries for tracking in Snowflake’s query history
  • Power analytics workflows with live data

​
Where to Use It

Add Snowflake as a tool to any agent. The agent can then query your data warehouse conversationally, choosing the right actions based on context. To add an MCP tool to your agent:
  1. Open your agent’s configuration
  2. Click Add tools → Connect an app with MCP
  3. Search for the integration and select it
  4. Authenticate with your account
You can control which tools your agent has access to. After adding an integration, click on it to enable or disable specific tools based on what your agent needs.

​
In Workflows (Via Agent Node)

For automated pipelines, use an Agent Node with Snowflake tools. This gives you the flexibility of an agent within a deterministic workflow.

​
As a Custom MCP Node

You can also create a standalone MCP node for a specific action. This generates a reusable node that performs one task, useful when you need the same operation repeatedly in workflows.
To create a custom MCP node:
  1. Go to your node library and search for the integration
  2. Click Create a node with AI
  3. Describe the specific action you want (e.g., “Query orders from last month”)
  4. Test the node and save it for reuse
Custom MCP nodes are single-purpose by design. For tasks that require multiple steps or dynamic decision-making, use an agent instead.

​
Available Tools

ToolDescription
Describe TableGet table structure and columns
Execute QueryRun a SQL query. Automatically injects a structured QUERY_TAG on every call for tracking in Snowflake’s QUERY_HISTORY.
Stage DataBulk load data into a table via staging

​
Example Prompts

Use these with your agent or in the Agent Node: Query data: 
Get all orders from last month with total over $1000
Check table schema: 
What columns are in the customers table?
Aggregate data: 
Show me daily revenue for the past 30 days
Run custom SQL: 
Run SELECT customer_id, SUM(amount) FROM orders GROUP BY customer_id
Run a tagged query: 
Run a query to get daily active users, tagged with "team:growth" for tracking
Bulk load data: 
Stage and load this CSV data into the customers table

​
Configuration Options

OptionDescriptionDefault
ocsp_fail_openAllow connection when OCSP certificate validation fails. Enable if encountering certificate validation errors with large queries.false
insecure_modeSkip OCSP certificate revocation checking entirely. Enable if encountering error 254007 on large result set downloads.false
Only enable insecure_mode if you are experiencing OCSP-related errors (e.g., error code 254007) when downloading large result sets. This disables certificate revocation checks on S3 result retrieval.

​
Troubleshooting

IssueSolution
Agent not finding the right dataSpecify schema and table names clearly
Action not completingCheck that you’ve authenticated with Snowflake
Unexpected resultsThe agent may chain multiple tools (e.g., describing a table first, then querying). Review the agent’s reasoning to understand its approach.
Tool not availableVerify the tool is enabled in your agent’s MCP configuration
Agents are smart enough to chain multiple API calls together. For example, asking “Query the sales table” will describe it first to understand the schema, then run the query. If results seem off, check the agent’s step-by-step reasoning.

​
Need Help?

Use this integration directly in Claude or Cursor. Connect remotely via the Snowflake MCP server using your Gumloop credentials.