How to Use the Snowflake MCP in VS Code Copilot

Q: How does VS Code Copilot help with data governance when interacting with Snowflake?

You can use listroles and listusers to audit who has access and what their roles are. This allows your team to verify that the code being written adheres to corporate security policies before merge.

Q: If I need to write a cross-schema report, how do I check Snowflake with VS Code Copilot?

Running listschemas and then listtables allows you to build scripts that cover multiple data domains. This gives the team full visibility into all potential sources within your Snowflake instance.

Q: What is the best way to track complex queries when using Snowflake with VS Code Copilot?

Use getstatementstatus paired with executesql. This mechanism provides a definitive status update (running, success, failure) for long-lived operations within your development workflow.

Q: If a user needs to know their current environment details on Snowflake with VS Code Copilot?

The getsessioncontext tool provides the necessary runtime details—user, warehouse, and database scope. This ensures that every developer is working against the assumed environment defined by your project.

Team configuration for Snowflake data access built directly into VS Code Copilot Chat.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Snowflake MCP to VS Code Copilot

Create your Vinkius account to connect Snowflake to VS Code Copilot — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Snowflake with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Check table structure with `describe_table`.

Need to know the exact column names and types? Use the `describe_table` tool inside your team's shared config. It pulls schema details instantly, so everyone gets the same accurate information when writing code for Snowflake. This prevents developers from guessing column names or assuming data formats. You just call it, and the necessary metadata is available to Copilot Chat’s agent mode.

Map out all accessible databases using `list_databases`.

Before starting a new project module, run `list_databases`. This lists every database your team can access on Snowflake. It's an instant inventory check for everyone working off the same repository. Similarly, use `list_schemas` and `list_tables` to narrow down exactly which data sets are relevant for the current feature branch.

Execute and monitor critical SQL jobs with `execute_sql`.

When your team runs a complex report, you need confirmation it finished. The `execute_sql` tool lets Copilot Chat run the query, while `get_statement_status` tracks its progress. You'll get results or a job handle without blocking the entire IDE. This is key for CI/CD pipelines; your code knows whether to proceed based on the real-time status returned by Snowflake.

Setup guide

Set up Snowflake MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Snowflake MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Snowflake tools listed. Try asking: "List my recent Snowflake transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "snowflake-alternative-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Snowflake. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Snowflake now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Snowflake MCP in VS Code Copilot

You can use `list_roles` and `list_users` to audit who has access and what their roles are. This allows your team to verify that the code being written adheres to corporate security policies before merge.

Running `list_schemas` and then `list_tables` allows you to build scripts that cover multiple data domains. This gives the team full visibility into all potential sources within your Snowflake instance.

Use `get_statement_status` paired with `execute_sql`. This mechanism provides a definitive status update (running, success, failure) for long-lived operations within your development workflow.

The server exposes names and identifiers for databases, schemas, tables, roles, users, and compute warehouses. This structured output is perfect for generating reference code within your team's codebase.

The `get_session_context` tool provides the necessary runtime details—user, warehouse, and database scope. This ensures that every developer is working against the assumed environment defined by your project.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript