MCPgee
MCPgee
MCPgeeMCPgee

Snowflake Cortex AI

v1.3.5•Databases•stable

🐍 ☁️ - Open-source MCP server for Snowflake from official Snowflake-Labs supports prompting Cortex Agents, querying structured & unstructured data, object management, SQL execution, semantic view querying, and more. RBAC, fine-grained CRUD controls,

snowflake-cortex-ai-mcp-servermcpai-integration
Share:
288
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Snowflake Cortex AI?

Snowflake Cortex AI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍 ☁️ - open-source mcp server for snowflake from official snowflake-labs supports prompting cortex agents, querying structured & unstructured data, object management, sql execution, semantic view que...

🐍 ☁️ - Open-source MCP server for Snowflake from official Snowflake-Labs supports prompting Cortex Agents, querying structured & unstructured data, object management, SQL execution, semantic view querying, and more. RBAC, fine-grained CRUD controls,

This server falls under the Databases and Cloud Services categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🐍 ☁️ - Open-source MCP server for Snowflake from official Sn

Use Cases

Query structured and unstructured data in Snowflake.
Execute SQL and manage database objects through natural language.
Leverage Snowflake Cortex Agents for advanced analytics.
Snowflake-Labs

Maintainer

LicenseApache 2.0
Languagepython
Versionv1.3.5
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y snowflake-labs-mcp

PIP

pip install snowflake-labs-mcp

Manual Installation

npx -y snowflake-labs-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Snowflake Cortex AI

The Snowflake Cortex AI MCP Server is an open-source server from Snowflake-Labs that bridges AI assistants with Snowflake's data platform and Cortex AI services. It enables natural language SQL execution, structured and unstructured data querying, Cortex Agent orchestration, Cortex Search for RAG workloads, Cortex Analyst for semantic modeling, and full Snowflake object management (databases, schemas, tables, warehouses, roles). Access is controlled through RBAC and fine-grained SQL permission settings defined in a YAML config file. Note: this community project is deprecated in favor of the official Snowflake MCP Server at docs.snowflake.com.

Prerequisites

  • Python 3.9 or newer with uv or pip installed
  • A Snowflake account with a user, role, and warehouse configured
  • Snowflake credentials: account identifier, username, and password or private key
  • A tools_config.yaml file specifying which Snowflake services and permissions to expose
  • An MCP client such as Claude Desktop
1

Install the package

Install snowflake-labs-mcp via pip or use uvx for isolated execution.

pip install snowflake-labs-mcp
2

Create a service configuration YAML

Create a tools_config.yaml file that declares which Snowflake services to enable (Cortex agents, search, analyst, object manager, query manager, semantic manager) and the SQL permission set.

# tools_config.yaml example
object_manager:
  enabled: true
query_manager:
  enabled: true
  sql_statement_permissions:
    - Select
    - Create
semantic_manager:
  enabled: true
3

Configure Claude Desktop

Add the MCP server entry to your Claude Desktop configuration file, pointing to your tools_config.yaml.

{
  "mcpServers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "snowflake-labs-mcp",
        "--service-config-file",
        "/path/to/tools_config.yaml",
        "--connection-name",
        "default"
      ],
      "env": {
        "SNOWFLAKE_ACCOUNT": "your_account_identifier",
        "SNOWFLAKE_USER": "your_username",
        "SNOWFLAKE_PASSWORD": "your_password",
        "SNOWFLAKE_ROLE": "SYSADMIN",
        "SNOWFLAKE_WAREHOUSE": "COMPUTE_WH"
      }
    }
  }
}
4

Verify the connection

Restart Claude Desktop and ask it to list available databases or run a simple SELECT query to confirm the server is connected.

5

Optional: run as an HTTP server for containerized deployments

To expose the MCP server over HTTP (e.g., from Docker), use the streamable-http transport.

uvx snowflake-labs-mcp --service-config-file config.yaml --transport streamable-http --endpoint /snowflake-mcp

Snowflake Cortex AI Examples

Client configuration

Claude Desktop configuration using uvx to run snowflake-labs-mcp with environment-based Snowflake credentials.

{
  "mcpServers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "snowflake-labs-mcp",
        "--service-config-file",
        "/path/to/tools_config.yaml",
        "--connection-name",
        "default"
      ],
      "env": {
        "SNOWFLAKE_ACCOUNT": "xy12345.us-east-1",
        "SNOWFLAKE_USER": "myuser",
        "SNOWFLAKE_PASSWORD": "mypassword",
        "SNOWFLAKE_ROLE": "DATA_ANALYST",
        "SNOWFLAKE_WAREHOUSE": "COMPUTE_WH"
      }
    }
  }
}

Prompts to try

Use these prompts in Claude Desktop once the Snowflake MCP server is connected.

- "List all databases in my Snowflake account."
- "Run a SELECT query on SALES_DB.PUBLIC.ORDERS and show me the top 10 rows by revenue."
- "Create a new schema called STAGING in the ANALYTICS database."
- "Query the semantic view for monthly revenue trends."
- "Use the Cortex Search service to find documents about Q3 product launches."
- "Describe the columns in the CUSTOMERS table."

Troubleshooting Snowflake Cortex AI

Authentication fails with 'incorrect username or password'

Verify SNOWFLAKE_ACCOUNT uses the full account identifier format (e.g., xy12345.us-east-1 or orgname-accountname). Check that SNOWFLAKE_USER and SNOWFLAKE_PASSWORD are correct, or switch to private key auth by setting SNOWFLAKE_PRIVATE_KEY_FILE.

SQL execution is blocked or returns a permission error

Check the sql_statement_permissions list in your tools_config.yaml — only statement types listed there will be allowed. Add the required type (e.g., 'Insert', 'Drop') to the permitted list.

uvx: command not found

Install uv via `pip install uv` or `curl -Ls https://astral.sh/uv/install.sh | sh`, then ensure the uv binary is on your PATH.

Frequently Asked Questions about Snowflake Cortex AI

What is Snowflake Cortex AI?

Snowflake Cortex AI is a Model Context Protocol (MCP) server that 🐍 ☁️ - open-source mcp server for snowflake from official snowflake-labs supports prompting cortex agents, querying structured & unstructured data, object management, sql execution, semantic view querying, and more. rbac, fine-grained crud controls, It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Snowflake Cortex AI?

Install via npm with the command: npx -y snowflake-labs-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Snowflake Cortex AI?

Snowflake Cortex AI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Snowflake Cortex AI free to use?

Yes, Snowflake Cortex AI is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Snowflake Cortex AI Alternatives — Similar Databases Servers

Looking for alternatives to Snowflake Cortex AI? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.

Excelize

★ 20.6k

Go language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets

MCP Toolbox for Databases

★ 15.3k

Open source MCP server specializing in easy, fast, and secure tools for Databases.

DBHub

★ 2.8k

A universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.

Tabularis

★ 2.1k

A lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.

Postgres AI Guide

★ 1.7k

MCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.

Anyquery

★ 1.7k

🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.

Browse More Databases MCP Servers

Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

DatabasesCloud ServicesBrowse All Servers

Quick Config Preview

{ "mcpServers": { "snowflake-cortex-ai-mcp-server": { "command": "npx", "args": ["-y", "snowflake-labs-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Snowflake Cortex AI?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides