Skip to main content The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery
Connectors Snowflake
Live 98 Actions

Snowflake Integration for AI Agents

Connect your AI agent to 98 QA'd Snowflake actions via MCP, A2A, or SDK, with agent authentication, tool-calling execution, and security built-in.

StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Snowflake AI Agent Actions

98 production-ready actions for your agent to do more on Snowflake.

98 Actions
List Databases - Retrieve list of all databases in the account
Fetch Database Details - Fetch metadata and properties of a specific database
Create Database - Create a new database in the Snowflake account
Update Database - Modify database properties like data retention or ownership
Delete Database - Drop a database and all its contained objects
Clone Database - Create a copy of an existing database with all its objects
Undrop Database - Restore a previously dropped database within the Time Travel retention period
List Functions - Get all user-defined functions in a schema
Fetch Function Details - Retrieve function signature and implementation
Delete Function - Drop a user-defined function
Create Function - Define a user-defined function in SQL, JavaScript, Python, Java, or Scala
Get Unified Credentials - Return the authenticated identity for the current Snowflake connection via the SQL API (SELECT CURRENT_USER, CURRENT_ROLE). Maps to the StackOne IAM unified credentials schema. auth_type is derived from the runtime credentials surface (api_key when a private key is present for Key Pair auth, otherwise oauth - both flows materialize an access token, so the private key is the discriminator).
List Unified Organizations - Return the Snowflake account as a single IAM organization record. Each connection targets exactly one Snowflake account identified by the Account Identifier configured during connection setup (format orgname-accountname). Always returns exactly one record with the Account Identifier as id/remote_id.
Get Unified Organization - Retrieve the Snowflake account as a single IAM organization. Each connection targets exactly one account - pass the id returned by unified_list_organizations (the Snowflake Account Identifier configured during connection setup).
List Unified Resource Types - List the resource types this Snowflake connector supports for resource-scoped permission queries. Always returns ["role"] - the only resource type with a grants-listing REST endpoint on this connector.
List Unified Resource Users - List the users granted a specific Snowflake role via the REST API, mapped to the StackOne IAM unified user schema with the queried role attached as a role-scoped entry. Currently supports resource_type "role" only.
List Unified Roles - List all roles in the connected Snowflake account via the REST API, mapped to the StackOne IAM unified role schema. Includes built-in system roles (ACCOUNTADMIN, SECURITYADMIN, SYSADMIN, USERADMIN, PUBLIC) and any custom roles. Fetches up to 30000 roles across a fixed 3-page fan-out (10000 per page); accounts beyond that are truncated.
Get Unified Role - Retrieve a single Snowflake role by name via the REST API, mapped to the StackOne IAM unified role schema. Role.id is the Snowflake role name (e.g. SYSADMIN, ACCOUNTADMIN). Implemented via filter on the /api/v2/roles list endpoint - Snowflake does not expose a direct GET /api/v2/roles/{name} REST endpoint.
List Unified Users - List all users in the connected Snowflake account via the REST API, mapped to the StackOne IAM unified user schema. Returns identity, status (enabled/disabled), email, name, and bot-user inference. Fetches up to 30000 users across a fixed 3-page fan-out (10000 per page); accounts beyond that are truncated. Pass expand=["roles"] to populate each user's default role.
Get Unified User - Retrieve a single Snowflake user by username via the REST API, mapped to the StackOne IAM unified user schema. Returns identity, status, email, and name. Pass expand=["roles"] to populate the user's default role.
List Pipes - Get all pipes in a schema
Fetch Pipe Details - Retrieve pipe configuration and status
Create Pipe - Set up Snowpipe for continuous data ingestion
Update Pipe - Modify pipe properties or COPY statement
Delete Pipe - Drop a Snowpipe object
List Procedures - Get all stored procedures in a schema
Fetch Procedure Details - Retrieve procedure definition and metadata
Create Procedure - Define stored procedure in SQL, JavaScript, Python, Java, or Scala
Delete Procedure - Drop a stored procedure
Call Stored Procedure - Execute a stored procedure with parameters
List Roles - Get all roles in the account
Create Role - Define a new role for access control
Delete Role - Drop a custom role
Grant Role To User - Assign a role to a user account
Revoke Role From User - Remove role assignment from a user
Grant Privileges To Role - Grant object privileges to a role for access control
List Grants To Role - List all privileges granted to a role
Revoke Privileges From Role - Revoke object privileges from a role
List Grants Of Role - List the users and roles this role has been granted to
List Grants On Role - List privileges granted on the role object itself
List Future Grants To Role - List future grants defined for a role
Grant Future Privileges To Role - Grant privileges on future objects to a role
Revoke Future Grants From Role - Revoke future-object privileges from a role
Set Tags On Role - Assign tag values to a ROLE (roles only)
Unset Tags From Role - Remove tag assignments from a ROLE (roles only)
Get Role Tags - Get the tag assignments for a ROLE (roles only)
List Schemas - Get all schemas in a specific database
Fetch Schema Details - Retrieve metadata for a specific schema
Create Schema - Create a new schema within a database
Update Schema - Modify schema properties like data retention or managed access
Delete Schema - Drop a schema and all its contained objects
Execute Query - Execute simple SELECT queries that complete within 45 seconds and return results immediately
Execute SQL Statement - Execute SQL statements with custom formatting and optional async execution for operations exceeding 45 seconds
Check Statement Status - Retrieve execution status, progress, and results for asynchronously submitted SQL statements
Get Statement Results - Retrieve an additional result partition (page) for a completed async SQL statement
Cancel Statement Execution - Terminate actively running SQL statements to reclaim compute resources and prevent unwanted operations
List Stages - Get all stages in a schema
Fetch Stage Details - Retrieve stage configuration and storage integration details
Create Stage - Create internal or external stage for data loading and unloading
Update Stage - Modify stage properties like file format or credentials
Delete Stage - Drop a stage object
List Streams - Get all streams in a schema
Fetch Stream Details - Retrieve stream metadata and current offset
Create Stream - Create change data capture stream on table or view
Delete Stream - Drop a stream object
List Tables - Retrieve all tables within a schema
Fetch Table Details - Fetch table metadata including columns, constraints, and statistics
Create Table - Create new permanent, transient, or temporary table
Update Table - Modify table properties like clustering keys or retention period
Delete Table - Drop a table and its data
Create Table As Select - Create a new table populated from a SQL SELECT query
Alter Table - Create or replace a table with updated structure and properties
Clone Table - Create a copy of an existing table with its data and structure
Undrop Table - Restore a previously dropped table within the Time Travel retention period
List Tasks - Get all tasks in a schema
Fetch Task Details - Retrieve task definition, schedule, and status
Create Task - Define scheduled or DAG-based task for automation
Update Task - Modify task schedule, definition, or warehouse
Delete Task - Drop a task object
Resume Task - Enable a suspended task to run on schedule
Suspend Task - Pause a running task to stop scheduled execution
Execute Task - Manually trigger a task to run immediately
List Users - Retrieve all user accounts in the account
Fetch User Details - Fetch user profile information and settings
Create User - Provision a new user account with authentication settings
Update User - Modify user properties like email, default role, or MFA settings
Delete User - Remove a user account from the system
List Views - Get all views in a schema
Fetch View Details - Retrieve view definition and metadata
Create View - Create standard, secure, or materialized view
Delete View - Drop a view
List Warehouses - Get all warehouses in the account
Fetch Warehouse Details - Retrieve warehouse configuration and current status
Create Warehouse - Provision a new virtual warehouse with specified size and properties
Delete Warehouse - Drop a virtual warehouse
Start Warehouse - Resume a suspended warehouse to begin processing queries
Suspend Warehouse - Pause a running warehouse to stop consuming credits
Alter Warehouse - Create or replace a warehouse with updated configuration (full property set required — omitted properties are reset to defaults)

Do More, Build Less

Integration Infrastructure for Snowflake AI Agents

Multiple Interfaces

Access integrations via API, AI SDKs, MCP & A2A.

Snowflake MCP server
Managed Authentication

Pre-built authentication UI.

Agent auth
Falcon Engine

Every Snowflake action runs on Falcon.

Agent Execution Engine
StackOne Defender
StackOne Defender Meta PG v1 Meta PG v2 DeBERTa 88.7% 67.5% 63.1% 56.9% Detection accuracy

88.7% prompt injection detection.

Prompt injection defense

"What impressed us most about StackOne is its ambition and clarity. They're creating infrastructure that modern software and the entire AI agent ecosystem can rely on. The depth of secure integrations, the pace of delivery, and the team's foresight into AI's future uniquely position StackOne to redefine this category."

Luna Schmid, Partner at GV

"We've been impressed by how quickly and deeply StackOne integrates with complex enterprise systems -- and now, with their focus on agent-to-agent interoperability, they're unlocking even more powerful use cases for customers. StackOne delivers all of the above in a universal layer -- without compromise."

Barbry McGann, SVP at Workday Ventures

G2 - High Performer G2 - Easiest To Do Business With G2 - Users Love Us G2 - Users Most Likely To Recommend G2 - Easiest Admin

Product Teams Love Building Agent Integrations With StackOne

G2

More Data Infrastructure Integrations Like Snowflake

Fivetran

172+ actions

Supabase

138+ actions

New Relic

135+ actions

Grafana

100+ actions

Render

98+ actions

Sentry

85+ actions

Honeycomb

79+ actions

Snowflake AI agent integration resources

How I Vibe-Coded a Customer Success Hub Using StackOne's AI Native Integration Platform

How a non-developer vibe-coded a customer success dashboard pulling HubSpot, Pylon, PostHog, Databricks, and Fireflies through StackOne's MCP gateway.

7 min read

Agentic Context Engineering: Why AI Agents Kill Their Own Context Windows

AI agents exceed their context windows without knowing it. Six failure patterns and seven survival architectures for agentic context engineering.

15 min

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.