Snowflake Stored Procedure Integration
Integrates and executes Snowflake stored procedures through an MCP server.
Snowflake Stored Procedure Integration with MCP Server
This project simplifies the integration of Snowflake stored procedures with an MCP (Model Context Protocol) server. It provides a framework to define, manage, and execute Snowflake procedures from the MCP server environment.
Requirements
- Python 3.8 or higher
uvinstalled
Installation
- Clone the repository:
git clone https://github.com/Cjaimesg/snowflake-mcp-sp-integration.git
cd snowflake-mcp-sp-integration
- Install dependencies using
uv:
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
Configuration
- Create a
.envfile in the root directory (do not commit this file). Define all required Snowflake credentials:
SNOWFLAKE_ACCOUNT=<xxx>-<xxx>
SNOWFLAKE_USER=<xxx>
SNOWFLAKE_PASSWORD=<xxx>
SNOWFLAKE_ROLE=<xxx>
SNOWFLAKE_WAREHOUSE=<xxx>
SNOWFLAKE_DATABASE=<xxx>
SNOWFLAKE_SCHEMA=<xxx>
SNOWFLAKE_HOST=<xxx>-<xxx>.snowflakecomputing.com
All variables are mandatory and must be defined by the user.
- Configure the project as an MCP server. In your MCP configuration file, add an entry like the following, adjusting the paths to match your local environment. Both --schemas and --procedures are optional and default to empty lists.
- Schemas: All store procedures in the specified schemas will be available to the MCP server.
- Procedures: Only the specified procedures will be available to the MCP server.
{
"mcpServers": {
"snowflake_sp_server": {
"command": "absolute/path/to/your/uv/uv.exe",
"args": [
"--directory",
"absolute/path/to/snowflake-mcp-sp-integration",
"run",
"main.py",
"--schemas",
"DB_NAME.SCHEMA_NAME",
"--procedures",
"DB_NAME.OTHER_SCHEMA_NAME.PROCEDURE_NAME"
]
}
}
}
Replace
absolute/path/to/snowflake-mcp-sp-integrationwith the actual directory where you cloned this repository.
Quickstart - Setup Guide for Dev Environment
The quickstart/ folder contains a step-by-step guide for setting up and testing this module in the Dev Environment.
License
This project is licensed under the MIT License.
Serveurs connexes
Membase MCP
A decentralized memory layer for AI agents providing secure, persistent storage for conversation history and knowledge.
GLEIF MCP Server
Access the Global Legal Entity Identifier (LEI) database for company verification, KYC, and corporate ownership research via GLEIF's public API.
Data ChileGob
MCP server exposing Chile's open government dataset portal (datos.gob.cl / CKAN API v3)
GeoServer MCP Server
Connects Large Language Models to the GeoServer REST API, enabling AI assistants to interact with geospatial data and services.
Swiss Truth MCP
Verified knowledge base for AI Agents — certified Swiss facts, no hallucinations.
ClickHouse
Query your ClickHouse database server.
Fabi Analyst Agent MCP
Fabi MCP is an autonomous agent that handles end-to-end data analysis tasks from natural language requests, automatically discovering data schemas, generating sql or python code, executing queries, and presenting insights.
Outreach.io by CData
A read-only MCP server for querying live data from Outreach.io using the CData JDBC Driver.
mnemon-mcp
Persistent layered memory for AI agents — 4-layer model, FTS5 search, fact versioning, EN+RU stemming. Local-first, zero-cloud, single SQLite file.
Kollect MCP Server (Standalone)
An MCP server for querying data from the Kollect tool's API endpoints, such as /api/data, /api/snapshots, and /api/costs.