a year ago
research-and-dataA Model Context Protocol (MCP) server that provides secure, read-only access to Snowflake databases. Allows LLMs to safely query tables and describe schemas without write permissions. Built with Python and the official Snowflake SDK.
Overview
What is MCP Snowflake Reader?
MCP Snowflake Reader is a read-only Model Context Protocol (MCP) server that provides secure access to Snowflake databases, allowing users to query tables and describe schemas without write permissions.
How to use MCP Snowflake Reader?
To use MCP Snowflake Reader, you can either run it using Docker or directly with Python. You need to set up a connection string with your Snowflake account details.
Key features of MCP Snowflake Reader?
- Secure, read-only access to Snowflake databases
- Compliance with MCP protocol
- Access control for databases, schemas, and tables
- Docker support for easy deployment
- API endpoints for listing databases, schemas, tables, and executing read-only queries
Use cases of MCP Snowflake Reader?
- Securely querying Snowflake databases without risk of data modification.
- Providing read-only access to data for analytics and reporting.
- Enabling LLMs to interact with Snowflake databases safely.
FAQ from MCP Snowflake Reader?
- Can I write data using MCP Snowflake Reader?
No, MCP Snowflake Reader only allows read-only access to ensure data integrity.
- What are the prerequisites for using MCP Snowflake Reader?
You need Python 3.10 or higher and a Snowflake account with appropriate permissions.
- Is Docker required to run MCP Snowflake Reader?
No, Docker is optional; you can also run it directly with Python.