Search and data
Snowflake for AI agents.
Managed auth, ready-made tools.
Browse databases, schemas and tables, run SQL and check query status in Snowflake on behalf of each of your users.
About Snowflake
With the Snowflake connector, your agent works in each user’s own Snowflake account with their own role. It can list databases, schemas and tables, describe a table’s columns, run a SQL statement and check or cancel it, using only the tools your project allows.
Snowflake is a cloud data platform for warehousing, analytics and data sharing.
Tools
What your agent can do in Snowflake.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Snowflake connection.
-
List databases
Readsnowflake_list_databasesList the databases the user's role can see.
-
List schemas
Readsnowflake_list_schemasList the schemas in a database.
-
List tables
Readsnowflake_list_tablesList the tables in a schema.
-
Describe a table
Readsnowflake_describe_tableGet a table's columns and their types.
-
Run SQL
Writesnowflake_run_queryRun a SQL statement in a warehouse and get the results.
-
Check a statement
Readsnowflake_get_statement_statusGet the status and results of a submitted statement.
-
Cancel a statement
Writesnowflake_cancel_statementCancel a running statement.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Snowflake, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent browse databases and tables, and switch off
snowflake_run_queryso it can never run SQL. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example browsing tables but not running statements. A call outside them is refused.
Get started
Connect Snowflake
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect Snowflake
Each end user authorizes their own Snowflake account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Snowflake account, once. const connection = await agent200 .user("user_123") .connect("snowflake"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the Snowflake tools
Name the user, the model and the tools. The model decides which Snowflake tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "What tables are in the analytics schema", tools: ["snowflake"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Who signs in
Each of your users, once, on Snowflake's own sign-in page. You never see or store their Snowflake password.
-
What access is requested
The access the connection needs, granted through the user's own Snowflake role and listed on Snowflake's authorization screen. Users can remove the app later from their Snowflake account settings.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Snowflake connector and how to use it.
Connector: Snowflake, through Agent200. In code: "snowflake". What it does: Browse databases, schemas and tables, run SQL and check query status in Snowflake on behalf of each of your users. Page: https://www.agent200.com/connectors/snowflake/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on Snowflake's own page, through the authorization link Agent200 returns. Never ask a user for a Snowflake password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: snowflake_list_databases, snowflake_list_schemas, snowflake_list_tables, snowflake_describe_table, snowflake_get_statement_status. Write tools: snowflake_run_query, snowflake_cancel_statement. Name "snowflake" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/snowflake/framework/claude/ https://www.agent200.com/connectors/snowflake/framework/chatgpt/ https://www.agent200.com/connectors/snowflake/framework/claude-code/ https://www.agent200.com/connectors/snowflake/framework/muse/ https://www.agent200.com/connectors/snowflake/framework/grok-bot/ https://www.agent200.com/connectors/snowflake/framework/openai-dots/ https://www.agent200.com/connectors/snowflake/framework/claude-duet/ https://www.agent200.com/connectors/snowflake/framework/hermes-agent/ https://www.agent200.com/connectors/snowflake/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/snowflake.md
Guides
Use Snowflake with the AI you build on.
Step-by-step setup for Snowflake with a specific model, assistant or agent framework.
-
Snowflake + Claude
How to connect Snowflake to Claude
-
Snowflake + ChatGPT
How to connect Snowflake to ChatGPT
-
Snowflake + Claude Code
How to connect Snowflake to Claude Code
-
Snowflake + Muse
How to connect Snowflake to Muse
-
Snowflake + Grok Bot
How to connect Snowflake to Grok Bot
-
Snowflake + OpenAI Dots
How to connect Snowflake to OpenAI Dots
-
Snowflake + Claude Duet
How to connect Snowflake to Claude Duet
-
Snowflake + Hermes Agent
How to connect Snowflake to Hermes Agent
-
Snowflake + OpenClaw
How to connect Snowflake to OpenClaw
FAQ
Snowflake and Agent200, answered.
Who handles the Snowflake OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Snowflake.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Snowflake connection, never another user's. It cannot reach anything the user or Snowflake has not authorized.
Can I limit what my agent can do in Snowflake?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.