Snowflake MCP | OAuth 2.0 Snowflake connector for AI agents

CALL ANY TOOL

List databases and schemas, inspect tables, run SQL queries under user role, and check query status and cost.

snowflake_databases_list

List databases

List all databases the user can access in Snowflake.

Parameters

Name

Type

Required

Description

—

No parameters required

snowflake_schemas_list

List schemas

snowflake_tables_list

List tables

snowflake_query_run

Run query

snowflake_query_status

Get query status

Build your Agent

Drop the toolkit in, point it at the user, and your analytics agent can use Snowflake from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["snowflake"], toolNames: ["snowflake_databases_list", "snowflake_schemas_list", "snowflake_tables_list"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["snowflake"], toolNames: ["snowflake_databases_list", "snowflake_schemas_list", "snowflake_tables_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["snowflake"], toolNames: ["snowflake_databases_list", "snowflake_schemas_list", "snowflake_tables_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/snowflake",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Snowflake.

Schema & discovery

Copy the prompt

Copied

List all databases in Snowflake.

Copy the prompt

Copied

Show schemas in [database].

Copy the prompt

Copied

List tables in [database.schema].

Copy the prompt

Copied

Get column types for [table].

Query & analysis

Copy the prompt

Copied

Weekly revenue by product line last 12 weeks.

Copy the prompt

Copied

Daily active users by tier last 30 days.

Copy the prompt

Copied

Top 10 accounts by API call volume this month.

Copy the prompt

Copied

Run: SELECT date_trunc('week', ts), sum(amount) FROM revenue GROUP BY 1 ORDER BY 1.

Monitoring & cost

Copy the prompt

Copied

Which queries used the most credits today?

Copy the prompt

Copied

Get status for query [id].

Copy the prompt

Copied

List tables updated in the last 24 hours.

Copy the prompt

Copied

Estimated cost for query: [SQL].

SEE HOW AUTH WORKS

Users authorize Snowflake once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Snowflake

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Snowflake

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Snowflake

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Snowflake

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other analytics agents and MCP connectors. Working code, live demos, fork what fits.

GTM

Salesforce customer insights agent

Surface Salesforce account activity, NPS signals, and renewal flags into Slack threads for the account team.

Salesforce

Slack

View agent

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Snowflake today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Snowflake as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Snowflake oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Snowflake?

Yes. Pass a tool name filter to listScopedTools so the analytics agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Snowflake.

What happens when a user revokes Snowflake access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Does the agent inherit the user's Snowflake role and row-level security?

Yes. Every query runs under the authorizing user's active Snowflake role. Row-level security policies, column masking, and object-level grants all apply. The agent cannot access data the user's role cannot reach.

Snowflake

Tools your analytics agent reaches for on Snowflake, scoped per user.