Snowflake MCP Server
A read-only server for interacting with Snowflake databases, allowing SELECT queries and access to schema context.
Snowflake MCP Server
Slightly altered from https://github.com/isaacwasserman/mcp-snowflake-server
Overview
A Model Context Protocol (MCP) server implementation that provides database interaction with Snowflake. This server enables running SQL queries via tools and exposes data insights and schema context as resources. Does not include the ability to execute write operations, and includes a system prompt.
Components
Resources
-
memo://insights
A continuously updated memo aggregating discovered data insights.
Updated automatically when new insights are appended via theappend_insighttool. -
context://table/{table_name}
(If prefetch enabled) Per-table schema summaries, including columns and comments, exposed as individual resources.
Tools
The server exposes the following tools:
Query Tools
read_query
ExecuteSELECTqueries to read data from the database.
Input:query(string): TheSELECTSQL query to execute
Returns: Query results as array of objects
Schema Tools
-
list_databases
List all databases in the Snowflake instance.
Returns: Array of database names -
list_schemas
List all schemas within a specific database.
Input:database(string): Name of the database
Returns: Array of schema names
-
list_tables
List all tables within a specific database and schema.
Input:database(string): Name of the databaseschema(string): Name of the schema
Returns: Array of table metadata
-
describe_table
View column information for a specific table.
Input:table_name(string): Fully qualified table name (database.schema.table)
Returns: Array of column definitions with names, types, nullability, defaults, and comments
Analysis Tools
append_insight
Add new data insights to the memo resource.
Input:insight(string): Data insight discovered from analysis
Returns: Confirmation of insight addition
Effect: Triggers update ofmemo://insightsresource
Usage with Claude Desktop
Installing via UVX
"mcpServers": {
"snowflake_pip": {
"command": "uvx",
"args": [
"--python=3.12", // Optional: specify Python version <=3.12
"mcp_snowflake_server",
"--account", "your_account",
"--warehouse", "your_warehouse",
"--user", "your_user",
"--password", "your_password",
"--role", "your_role",
"--database", "your_database",
"--schema", "your_schema"
// Optionally: "--log_dir", "/absolute/path/to/logs"
// Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
// Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
]
}
}
Installing Locally
-
Install Claude AI Desktop App
-
Install
uv:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Create a
.envfile with your Snowflake credentials:
SNOWFLAKE_USER="xxx@your_email.com"
SNOWFLAKE_ACCOUNT="xxx"
SNOWFLAKE_ROLE="xxx"
SNOWFLAKE_DATABASE="xxx"
SNOWFLAKE_SCHEMA="xxx"
SNOWFLAKE_WAREHOUSE="xxx"
SNOWFLAKE_PASSWORD="xxx"
# Alternatively, use external browser authentication:
# SNOWFLAKE_AUTHENTICATOR="externalbrowser"
-
[Optional] Modify
runtime_config.jsonto set exclusion patterns for databases, schemas, or tables. -
Test locally:
uv --directory /absolute/path/to/mcp_snowflake_server run mcp_snowflake_server
- Add the server to your
claude_desktop_config.json:
"mcpServers": {
"snowflake_local": {
"command": "/absolute/path/to/uv",
"args": [
"--python=3.12", // Optional
"--directory", "/absolute/path/to/mcp_snowflake_server",
"run", "mcp_snowflake_server"
// Optionally: "--log_dir", "/absolute/path/to/logs"
// Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
// Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
]
}
}
Notes
- The server supports filtering out specific databases, schemas, or tables via exclusion patterns.
- The server exposes additional per-table context resources if prefetching is enabled.
- The
append_insighttool updates thememo://insightsresource dynamically.
License
MIT
相关服务器
MCP Persistence
MCP Persistence: your AI Agent now creates and manages databases on its own
Mantora
Mantora is a local-first MCP observer: a lightweight UI + proxy for inspecting LLM data access (sessions, tool calls, results) with protective defaults.
Octodet Elasticsearch MCP Server
An MCP server for interacting with Elasticsearch clusters, enabling LLM-powered applications to search, update, and manage data.
MySQL Server Pro
A MySQL server with CRUD operations, database anomaly analysis, and support for SSE and STDIO.
Advanced Memory Bank MCP
An intelligent memory management server with 14 optimized tools. It provides AI-powered summaries, a clean interface, and supports an optional PostgreSQL database with pgvector.
Google BigQuery by CData
Connect to Google BigQuery databases using CData's MCP Server. Requires a separate CData JDBC Driver license.
USDA Nutrition MCP Server
Access nutrition information for over 600,000 foods from the USDA FoodData Central database.
VikingDB
A server for storing and searching data in a VikingDB instance, configurable via command line or environment variables.
Kusto MCP Server
An MCP server for Azure Data Explorer (Kusto) that enables AI assistants to interact with Kusto databases.
MongoDB Mongoose MCP
An MCP server for MongoDB with optional Mongoose schema support.