Snowflake MCP connector
The Snowflake connector lets Claude, ChatGPT, Cursor and other AI clients manage Snowflake users, roles, warehouses, views, alerts and accounts on your behalf, with every action limited to your own Snowflake access and recorded in an audit log.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
205 tools
How to connect
How to connect Snowflake to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Snowflake once
-
Open Connections, choose Add connection, and pick Snowflake.
-
Optionally set Share with to give a team access, then press Connect.
-
Supply your own Snowflake app, then approve. Snowflake needs an OAuth app you register yourself, so bring its client ID and secret. One person does this once for the organization.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Snowflake MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Snowflake MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Snowflake MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Snowflake to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Snowflake through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Data engineering
Create a view without opening a worksheet
Describe the view you need and have it created in the right database and schema, then confirm it is there before pointing a dashboard at it.
-
Data platform
Onboard a new analyst in one ask
Create the Snowflake user, grant the right role and check the warehouse they will use, all from the same conversation that started with the hiring ticket.
-
Security
Review who holds which Snowflake roles
Pull the full list of Snowflake users and roles ahead of an access review, spot accounts that should have been removed and clean them up on the spot.
-
Analytics
Set up alerts on the numbers that matter
Create a Snowflake alert for a threshold your team watches, run it once to check the condition is right, then clone it for a second region.
-
Finance
See every warehouse before the bill arrives
List the warehouses in your Snowflake account, ask which ones were created recently, and stand up a properly sized one for a new project instead of reusing the biggest.
-
IT
Offboard a leaver cleanly from Snowflake
Remove the departed person's Snowflake user and the roles nobody else needs, and if an account was dropped by mistake, restore it without a support ticket.
Try asking
- “List Snowflake roles created in the last 30 days.”
- “Which Snowflake users have no role assigned?”
- “Show open Snowflake alerts by account.”
Compare
Elaichi vs Zapier MCP vs Composio for Snowflake
All three can connect Snowflake to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Snowflake tools | Allow or restrict single Snowflake tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Snowflake call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
AI tools
Snowflake tools for your AI agents
205 tools are ready to call through Elaichi's MCP endpoint the moment you connect Snowflake, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Snowflake gets you
6 screens from the product, each doing one job for your Snowflake account.
The agent
Ask about Snowflake users in plain language.
Starter prompts return live answers from Snowflake users, roles, accounts and alerts.
- users
- roles
- accounts
- alerts
Ask Elaichi to work across your apps.
List Snowflake roles created in the last 30 days.
Which Snowflake users have no role assigned?
Show open Snowflake alerts by account.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor share one endpoint.
Every MCP client reaches Snowflake over OAuth, with no SDK and no shared key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
205 Snowflake tools are ready to call.
Browse tool names, resources and methods for users, roles, accounts and alerts.
- List all Snowflake users
- Get single Snowflake user by ID
- Delete a Snowflake user by ID
- Create a Snowflake user
ElaichiToolsToolboxes
Every team gets its own Snowflake toolbox.
Curate one toolbox per team, each scoped to the Snowflake work it does.
- Data platform
- Analytics engineering
- Security
- Finance
ElaichiToolboxesShared connections
Teammates query Snowflake without touching credentials.
See who connected each Snowflake account and how many teams and members share it.
- Data platform
- Analytics EMEA
- Security
- Finance
ElaichiConnectionsAudit log
Every Snowflake call is on the record.
When, who, what happened, type and resource for each role and account change.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule drafts your Snowflake digest.
Fetch alerts, group them, draft a digest, get approval, post back to Snowflake.
Snowflake digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch users
Snowflake
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Snowflake
Queued
Collections and dashboards
Snowflake health numbers arrive already computed.
Four metrics, 14 days of records created and a team breakdown, refreshed on schedule.
Snowflake health
Refreshed 4 minutes ago · every 15 minutes · from the users collection
Users
1,284 ↓ 12%
Roles
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Users created
Last 14 days
By team
Share of activity
Data platform 34%
Analytics EMEA 27%
Security 21%
Finance 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Snowflake to Claude?
First connect Snowflake in Elaichi, then in Claude go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Snowflake requires an OAuth application registered inside your Snowflake account, so one administrator brings a client ID and secret once during setup; after that, everyone signs in to Snowflake with their normal username and password and nobody else touches a credential. Because Snowflake exposes a large number of actions, short concrete asks such as "list the warehouses" get better results than long paragraphs.
Does Snowflake work with ChatGPT and Cursor as well as Claude?
Yes. Once Snowflake is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, the Elaichi Agent and any other MCP client. You connect Snowflake once and every client you use picks it up.
What can an AI agent actually do with my Snowflake account?
With Snowflake connected, an AI agent can list, create, update and remove Snowflake users, list and create roles, list and create warehouses, create and look up views, and set up, run and clone alerts. It can also list Snowflake accounts, create new ones and restore an account that was dropped. It works on live records in your Snowflake account, so an answer about who has which role reflects what is true right now.
Does connecting Snowflake give the AI access to everything in my account?
No. Every action runs as the person who signed in to Snowflake, so the AI can only see and change what that person's own Snowflake roles already allow. Elaichi can narrow that further by hiding actions from a team, but it can never grant anything the person's Snowflake account does not already have.
Can I stop an agent from deleting or changing things in Snowflake?
Yes. Restrictions in Elaichi apply per action, so you can allow listing Snowflake users, roles and warehouses while blocking the actions that delete users, drop views or remove accounts. A blocked action is never shown to Claude, ChatGPT, Cursor or any other client, so no prompt, however worded, can reach it.
What happens to a Snowflake connection when someone leaves?
When you offboard a person in Elaichi, their access to Snowflake through every AI client ends at once. A shared Snowflake connection keeps working for everyone else on the team. If you ever want to remove Snowflake entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.
Does the Snowflake MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Snowflake is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Snowflake?
Yes. Both let Claude, ChatGPT or Cursor use Snowflake. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Snowflake call.
How is Elaichi different from Composio for Snowflake?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Snowflake: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Snowflake in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.