Supports configuration through environment variables loaded from .env files, allowing users to store Snowflake credentials and connection parameters securely.
Formats query results in Markdown format, making the data more readable and structured when displayed in supported interfaces.
Provides tools for interacting with Snowflake databases, including executing SQL queries, listing warehouses, databases, and views, describing view details, and querying views with options for read-only mode and formatted results.
Simple Snowflake MCP server
Simple Snowflake MCP Server to work behind a corporate proxy (because I could not get that in a few minutes with existing servers, but my own server, yup). Still don't know if it's good or not. But it's good enough for now.
Tools
The server exposes the following MCP tools to interact with Snowflake:
- execute-snowflake-sql: Executes a SQL query on Snowflake and returns the result (list of dictionaries)
- list-snowflake-warehouses: Lists available Data Warehouses (DWH) on Snowflake
- list-databases: Lists all accessible Snowflake databases
- list-views: Lists all views in a database and schema
- describe-view: Gives details of a view (columns, SQL)
- query-view: Queries a view with an optional row limit (markdown result)
- execute-query: Executes a SQL query in read-only mode (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH) or not (if
read_only
is false), result in markdown format
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
- Build package distributions:
This will create source and wheel distributions in the dist/
directory.
- Publish to PyPI:
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--token
orUV_PUBLISH_TOKEN
- Or username/password:
--username
/UV_PUBLISH_USERNAME
and--password
/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm
with this command:
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
New Feature: Snowflake SQL Execution
The server exposes an MCP tool execute-snowflake-sql
to execute a SQL query on Snowflake and return the result.
Usage
Call the MCP tool execute-snowflake-sql
with a sql
argument containing the SQL query to execute. The result will be returned as a list of dictionaries (one per row).
Example:
The result will be returned in the MCP response.
Installation and configuration in VS Code
- Clone the project and install dependencies
- Configure Snowflake access
- Copy
.env.example
to.env
(or create.env
at the root) and fill in your credentials:
- Copy
- Configure VS Code for MCP debugging
- The
.vscode/mcp.json
file is already present: - Open the command palette (Ctrl+Shift+P), type
MCP: Start Server
and selectsimple-snowflake-mcp
.
- The
- Usage
- The exposed MCP tools allow you to query Snowflake (list-databases, list-views, describe-view, query-view, execute-query, etc.).
- For more examples, see the MCP protocol documentation: https://github.com/modelcontextprotocol/create-python-server
Supported MCP Functions
The server exposes the following MCP tools to interact with Snowflake:
- execute-snowflake-sql: Executes a SQL query on Snowflake and returns the result (list of dictionaries)
- list-snowflake-warehouses: Lists available Data Warehouses (DWH) on Snowflake
- list-databases: Lists all accessible Snowflake databases
- list-views: Lists all views in a database and schema
- describe-view: Gives details of a view (columns, SQL)
- query-view: Queries a view with an optional row limit (markdown result)
- execute-query: Executes a SQL query in read-only mode (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH) or not (if
read_only
is false), result in markdown format
For each tool, see the Usage section or the MCP documentation for the call format.
This server cannot be installed
Simple Snowflake MCP Server to work behind a corporate proxy.
Related MCP Servers
- -securityAlicense-qualityA Model Context Protocol server that provides access to Snowflake databases for any MCP-compatible client, allowing execution of SQL queries with automatic connection management.Last updated -2PythonMIT License
- -securityAlicense-qualityA proxy service that connects MCP clients to remote MCP servers, allowing users to use server keys from MCP.so to access remote resources without running their own server.Last updated -4092TypeScriptMIT License
- -security-license-qualityProxy that aggregates multiple MCP servers and presents them as a unified interface, allowing clients to access resources from multiple servers transparently.Last updated -1TypeScript
- JavaScriptMIT License