Sign in Book a demo
Back to Tools
Databases OAuth
Build Your Agent View Snowflake Docs
snowflake logo

Snowflake MCP Tools for AI Agents

Let an agent discover accessible databases, inspect schemas and tables, read column definitions, and run read-only SELECT queries in Snowflake.

Available Tools

7 tools available in this integration

Snowflake.DiscoverDatabases

List the databases your role can access, newest-created first.

Snowflake.DiscoverSchemas

List the schemas in a database that your role can access.

Snowflake.DiscoverTables

List the tables and views in a schema that your role can query.

Snowflake.DiscoverWarehouses

List the warehouses your role can run queries on.

Snowflake.ExecuteSelectQuery

Run a read-only SELECT query and return the rows.

Snowflake.GetTableSchema

Get a table or view's columns, so you can select exact fields.

Snowflake.WhoAmI

Return the Snowflake identity every other tool uses, and the warehouse.

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find the right Snowflake table for monthly revenue and show me the columns before querying it." Arcade helps it use the right Snowflake actions without guessing database, schema, table, or warehouse identifiers.

Up to 100x fewer tokens

Snowflake discovery and schema reads return focused lists of databases, schemas, tables, views, warehouses, and columns. The agent can narrow the search before loading query results or unrelated catalog content into the model.

Complete the workflow end to end

Identify the Snowflake account and warehouse, discover the relevant database and schema, inspect table columns, run a read-only query, and return the rows with the SQL through one toolkit designed around the complete data analysis task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Snowflake

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Snowflake, you can implement some of these policies:

Access when tools are listed for a user
  • Decide which tools an agent is allowed to see at all. A tool that is never listed cannot be called, whoever is asking.
Pre-execution before each tool call
  • Inspect the inputs a call is about to run with, and block it or send it for human approval when they fall outside what the agent should do unsupervised.
Post-execution after the tool returns
  • Redact Snowflake.ExecuteSelectQuery results, removing Social Security numbers, payment card numbers, email addresses, and phone numbers before they reach the model.
  • Deny Snowflake.DiscoverDatabases output when it includes databases on your restricted-data list, so an agent cannot learn the names of regulated or confidential data stores.
  • Strip Snowflake.WhoAmI results of account identifiers and role details before the model sees them, retaining only the warehouse needed to plan a query.

How to use Snowflake with your agent

Connect Snowflake to an MCP client through Arcade, then authorize each user's Snowflake account and start querying the data their role can access.

Your questions, answered

A Snowflake MCP server exposes Snowflake operations as structured tools that an AI agent can call through the Model Context Protocol. After a user authorizes Snowflake, the agent can discover accessible databases, schemas, tables, views, and warehouses, then run read-only SELECT queries under that user's role.

Arcade provides MCP access to Snowflake with per-user OAuth, agent-oriented discovery and query actions, and a common runtime for approval, redaction, and client access. Policies can govern Snowflake calls consistently across users, agents, and frameworks.

Arcade agents can identify the authorized Snowflake user and warehouse, list accessible databases, schemas, tables, and views, inspect exact columns, and run read-only SELECT queries. They cannot insert, update, delete, create, or alter Snowflake data through these actions.

Each user authorizes their own Snowflake account, and calls run with the privileges of the active Snowflake role. That role must be able to access the relevant databases and schemas, query the selected tables or views, and run queries on an available warehouse.

Yes. Each user authorizes their own Snowflake account through OAuth. The agent can access only the databases, schemas, tables, views, and warehouses available to that user's authorized Snowflake role.

Yes. Contextual Access policies can require human approval before a Snowflake query or other selected call proceeds, redact fields from query results, or hide an action from the agent entirely. All actions shipped here are read-only, so approval is about controlling access to data and query execution rather than approving writes.

Arcade proxies Snowflake API calls and does not persist your query results or other content as part of normal tool execution. OAuth credentials are brokered and stored encrypted at rest, and the model never receives them.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the user's Snowflake authorization remains valid. If it is revoked, rotated, or can no longer be refreshed, calls stop until the user reconnects Snowflake.

Queries remain subject to Snowflake's account, role, warehouse, concurrency, and resource limits. Arcade does not grant access beyond the user's Snowflake permissions or expand the capacity of the warehouse running the query.

Ready to actually ship your agent?

Connect your agent to Snowflake with managed OAuth, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Snowflake Quickstart