Snowflake Cortex MCP Server - NodeJS

@thisisbhanuj

Basic information

About Snowflake Cortex MCP Server - NodeJS

This Snowflake MCP server provides tooling for Snowflake Cortex AI features, bringing these capabilities to the MCP ecosystem. When connected to an MCP Client (e.g. Claude for Desktop, fast-agent, Agentic Orchestration Framework), users can leverage these Cortex AI features.

#snowflake#cortex#ai #nodejs #typescript

Snowflake Cortex MCP Server - NodeJS config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Cortex Agent AI": {
      "command": "ABSOLUTE_PATH\\nodejs\\npx.cmd",
      "args": [
        "tsx",
        "--watch",
        "--env-file",
        "ABSOLUTE_PATH\\snowflake-cortex-mcp\\.env",
        "ABSOLUTE_PATH\\snowflake-cortex-mcp\\src\\mcp\\MCP.ts"
      ]
    }
  }
}

Snowflake Cortex MCP Server - NodeJS tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Snowflake Cortex MCP Server - NodeJS?

A Model Context Protocol server that provides tooling for Snowflake Cortex AI features, enabling queries on structured and unstructured data via MCP clients. It supports Cortex Search, Cortex Analyst, and Cortex Agent.

How to use Snowflake Cortex MCP Server - NodeJS?

Run yarn dev to start the server. Configure connection using environment variables, including SNOWFLAKE_PAT for Programmatic Access Token. Integrate with an MCP client (e.g., Claude Desktop, VS Code + Copilot) by adding the server to the client’s configuration file.

Key features of Snowflake Cortex MCP Server - NodeJS

Query unstructured data using Cortex Search.
Query structured data via Cortex Analyst with semantic models.
Use Cortex Agent for multi‑step data orchestration.
Dynamically build agent requests with Payload Builder.
Works with multiple MCP clients (Claude Desktop, VS Code Copilot, etc.).
Authenticates via Programmatic Access Tokens.

Use cases of Snowflake Cortex MCP Server - NodeJS

Build a natural language data assistant in VS Code with Copilot.
Enable RAG workflows by querying unstructured Snowflake data.
Convert natural language questions into SQL queries via Cortex Analyst.
Orchestrate complex queries across structured and unstructured data with Cortex Agent.

Frequently asked questions

How do I connect to Snowflake?

Use a Programmatic Access Token (PAT) set as the environment variable `SNOWFLAKE_PAT`.

How do I try this?

The MCP server is meant to be used with an MCP client as orchestrator. See the MCP Introduction for details.

Where is this deployed? Is this in Snowpark Container Services?

All tools are managed services available via REST API. No separate remote deployment is required; the MCP client starts the server locally.

I'm receiving permission errors from my tool calls.

Programmatic Access Tokens do not evaluate secondary roles. Create a PAT with a single role that has access to all required services, or select “any role” when creating the token.