Snowflake + ChatGPT

How to connect Snowflake to ChatGPT

Set up Snowflake for ChatGPT with Agent200, then check which tools are available to your agent.

On this page
  1. Overview
  2. Before you start
  3. Setup steps
  4. Test your connection
  5. Instructions for AI agents
  6. Snowflake tools
  7. How it works
  8. Troubleshooting

Overview

This guide connects Snowflake to ChatGPT through Agent200. When you finish, ChatGPT can call the Snowflake tools for each of your users.

Every call runs with that user's own Snowflake connection: Agent200 runs the OAuth flow, stores and refreshes the tokens, and executes the call. You do not build or maintain a Snowflake integration.

Connector
Snowflake
Works with
ChatGPT ยท Your own agent code
Authentication
Managed OAuth, per end user
Tools
7 tools
Model in examples
openai/gpt-5.6-sol

Before you start

  • An Agent200 API key. Create one on the API keys page of the dashboard.
  • Snowflake enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
  • An end user with a Snowflake account. They approve access once, on Snowflake's own page.
  • A model for your agent. The examples use openai/gpt-5.6-sol, through the same Agent200 API key.

Connect Snowflake to ChatGPT

  1. 1

    Step 1: Create your Agent200 API key

    Open the API keys page in the Agent200 dashboard and choose Create an API key. Copy the key and store it as an environment variable, AGENT200_API_KEY, or in your secrets manager. One key covers Snowflake and every other connector and model enabled for your project. Keep it out of chats, prompts and source control.

    .env
    Conceptual example
    Store the Agent200 API key as an environment variable
    # Keep the key out of your code, prompts and chats.
    export AGENT200_API_KEY="paste-your-key-here"
  2. 2

    Step 2: Set up the Agent200 SDK

    Add the SDK to your project and create a client with the key from the environment.

    agent.js
    Conceptual example
    Set 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,
    });
  3. 3

    Step 3: Let your user connect Snowflake

    Each end user authorizes their own Snowflake account once, through managed OAuth. If the user has not connected yet, Agent200 returns an authorization link: show it to them, and they approve access on Snowflake's own page. Agent200 handles the callback, stores the tokens and refreshes them.

    connect.js
    Conceptual example
    Let 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);
    }
  4. 4

    Step 4: Run with the Snowflake tools

    Name the user, the model and Snowflake in the tools. The model decides when a Snowflake tool is needed, and Agent200 executes the call with the user's own connection.

    run.js
    Conceptual example
    Run 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);

Test your connection

Run one request to check everything is wired up.

Ask

Ask ChatGPT to list the Agent200 tools available for Snowflake, including which are read-only.

What should come back

  • A list of the Snowflake tools enabled for this Agent200 project, with their names and descriptions. If no tools appear, check that the connector is available to the project and its tools are enabled.

If no tools appear, check your Agent200 project access for Snowflake and make sure its tools are enabled. Tool availability depends on your project setup.

Get your API key

Create a key in the Agent200 dashboard. It reaches Snowflake and every other connector enabled for your project.

Read the SDK docs

Instructions for AI agents

Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect Snowflake to ChatGPT.

Agent brief
Goal: connect Snowflake to ChatGPT with Agent200.
Guide: https://www.agent200.com/connectors/snowflake/framework/chatgpt/

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. Make sure Snowflake is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's Snowflake account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on Snowflake.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "snowflake" in the tools. The model decides when a Snowflake tool is needed; Agent200 executes the call.
7. Check it works with this request: "Ask ChatGPT to list the Agent200 tools available for Snowflake, including which are read-only."
   What should come back:
   - A list of the Snowflake tools enabled for this Agent200 project, with their names and descriptions. If no tools appear, check that the connector is available to the project and its tools are enabled.
8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in Snowflake, then retry.

The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

The whole guide is also available as Markdown, for agents and LLMs: /connectors/snowflake/framework/chatgpt.md

Snowflake tools ChatGPT can call

  • List databases

    Read
    snowflake_list_databases

    List the databases the user's role can see.

  • List schemas

    Read
    snowflake_list_schemas

    List the schemas in a database.

  • List tables

    Read
    snowflake_list_tables

    List the tables in a schema.

  • Describe a table

    Read
    snowflake_describe_table

    Get a table's columns and their types.

  • Run SQL

    Write
    snowflake_run_query

    Run a SQL statement in a warehouse and get the results.

  • Check a statement

    Read
    snowflake_get_statement_status

    Get the status and results of a submitted statement.

  • Cancel a statement

    Write
    snowflake_cancel_statement

    Cancel a running statement.

How it works

  1. 01

    Your app sends the request

    It calls Agent200 with the model, instructions, the input, the end user's id and the Snowflake tools.

  2. 02

    The model picks a tool

    The model decides whether a Snowflake tool is needed, and with which arguments.

  3. 03

    Agent200 runs the call

    It uses that user's own Snowflake connection, within the endpoints and scopes your project allows, and returns the result to the model.

  4. 04

    Your app gets the result

    Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's Snowflake account.

Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and Snowflake enforces what its API grants.

Troubleshooting

Why not add Agent200 to ChatGPT as an MCP server?

ChatGPT’s custom MCP servers sign in with OAuth or with no sign-in, and cannot send an API key. Agent200’s MCP server uses your API key, so for ChatGPT users the SDK route on this page is the one that works.

The request says Snowflake authorization is required

The end user has not connected Snowflake yet, or the connection needs to be approved again. Agent200 returns an authorization link: show it to the user, let them approve access on Snowflake's own page, then run the request again.

ChatGPT does not use the Snowflake tools

Check that Snowflake is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming Snowflake in the request, or in the instructions, also helps the model choose the right tool.

A tool call is refused or returns less than expected

Agent200 runs only what your project allows (services, endpoints and scopes), and Snowflake returns only what the end user authorized. Widen the endpoints or scopes in the dashboard if the agent needs more, then ask the user to connect Snowflake again so they can approve the new access.

The results come from the wrong account

Every request names an end user (user_123 in the examples). Pass the id of the person your agent is working for: Agent200 then uses only that user's Snowflake connection, never another user's.

The API key was pasted into a chat or committed

Create a new key on the API keys page, update AGENT200_API_KEY wherever your app reads it, and stop using the old one. Keep keys in environment variables or a secrets manager, never in prompts, chats or source control.

Use Snowflake with another framework

200 OK

Snowflake, connected to ChatGPT.
One SDK. One API key.

Agent200 handles the OAuth, the tokens and every tool call. You keep your agent, your model and your code.

Book a demo.
See it in action.

Tell us who you are, then pick a time for a 1:1 session with an expert from our team.

We use your details only to email you about Agent200. See the Privacy Policy.

Pick a time. We'll take it from there.

A 1:1 session with an expert from our team, about what you are building.

Open in Calendly (opens in a new tab)