Fresha Reports via Snowflake
199-mcpLABSCO SUMMARY
Scope is set at launch, not left to the model.
Generic SQL servers hand a model the whole account and hope the prompt holds. This inverts that: the tool list is whatever you named on the command line, so a procedure that was not nominated is not reachable at all. The other benefit is that the business logic lives in reviewed, version-controlled procedures rather than being re-derived by a model on each call. The Snowflake role you configure still bounds everything, so give it the narrowest grants that work.
What it is
A framework that turns Snowflake stored procedures into callable MCP tools. You name either the schemas or the individual procedures at launch; those become the server's tool surface, so a model calls a procedure your team already wrote and reviewed rather than composing SQL.
What you get
- The procedures you nominate become the tools, so the logic stays where your team maintains it
- Two ways to scope:
--schemasexposes every stored procedure in the schemas you name,--proceduresexposes only the fully qualified procedures you list - Both flags are optional and default to empty lists, so nothing is exposed until you say what to expose
- Credentials stay in the environment rather than in the tool call
- A quickstart folder with a step-by-step setup for a development environment
Requirements
Python 3.8 or higher and uv. Every Snowflake connection variable is mandatory and comes from a .env file you create: SNOWFLAKE_ACCOUNT, SNOWFLAKE_USER, SNOWFLAKE_PASSWORD, SNOWFLAKE_ROLE, SNOWFLAKE_WAREHOUSE, SNOWFLAKE_DATABASE, SNOWFLAKE_SCHEMA and SNOWFLAKE_HOST. The client launches uv against the repository directory with main.py and the scope flags appended.
Setup effort
Build from source — git clone https://github.com/Cjaimesg/snowflake-mcp-sp-integration.git
USE CASES
01
Letting an assistant run a reviewed procedure
Expose the procedure your team already wrote and let the model call it with arguments instead of writing SQL.
02
Keeping a model away from the rest of the account
Name only the procedures you intend to expose; nothing else appears in the tool list.
03
Opening a whole schema for a trusted workflow
Point the schema flag at one schema so every procedure in it becomes available at once.
04
Standing it up in a development account first
Follow the quickstart to wire and test the integration before it touches production.
BEFORE YOU INSTALL
What to know first
Requires
- Python 3.8 or later
- SNOWFLAKE_ACCOUNT in your environment
- SNOWFLAKE_PASSWORD in your environment
- SNOWFLAKE_USER in your environment
- SNOWFLAKE_ROLE in your environment
- SNOWFLAKE_WAREHOUSE in your environment
- SNOWFLAKE_DATABASE in your environment
- SNOWFLAKE_SCHEMA in your environment
- SNOWFLAKE_HOST in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/Cjaimesg/snowflake-mcp-sp-integration.git
cd snowflake-mcp-sp-integration
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activateCreate a .env file in the root directory with:
FILE · .env
SNOWFLAKE_ACCOUNT=<YOUR_SNOWFLAKE_ACCOUNT>
SNOWFLAKE_USER=<YOUR_SNOWFLAKE_USER>
SNOWFLAKE_PASSWORD=<YOUR_SNOWFLAKE_PASSWORD>
SNOWFLAKE_ROLE=<YOUR_SNOWFLAKE_ROLE>
SNOWFLAKE_WAREHOUSE=<YOUR_SNOWFLAKE_WAREHOUSE>
SNOWFLAKE_DATABASE=<YOUR_SNOWFLAKE_DATABASE>
SNOWFLAKE_SCHEMA=<YOUR_SNOWFLAKE_SCHEMA>
SNOWFLAKE_HOST=<YOUR_SNOWFLAKE_HOST>Add the mcpServers entry below to your MCP configuration file
MCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"snowflake_sp_server": {
"command": "<YOUR_PATH_TO_UV>/uv.exe",
"args": [
"--directory",
"<YOUR_PATH_TO_SNOWFLAKE_MCP_SP_INTEGRATION>",
"run",
"main.py",
"--schemas",
"DB_NAME.SCHEMA_NAME",
"--procedures",
"DB_NAME.OTHER_SCHEMA_NAME.PROCEDURE_NAME"
]
}
}
}
