runekaagaard/mcp-alchemy

What it solves

MCP Alchemy provides a bridge between Claude Desktop and various SQL databases, allowing users to interact with their data using natural language. It removes the need for users to manually write and execute SQL queries by enabling an LLM to explore database structures, validate queries, and analyze datasets directly.

How it works

The project implements the Model Context Protocol (MCP) to expose database tools to Claude. It leverages SQLAlchemy to maintain compatibility with a wide range of databases including PostgreSQL, MySQL, MariaDB, SQLite, Oracle, MS SQL Server, CrateDB, and Vertica. The server can be configured via DB_URL and supports both stdio and HTTP transports (streamable-http and SSE).

Who it’s for

Developers and data analysts who use Claude Desktop and want to integrate their local or remote databases for automated exploration, query writing, and reporting.

Highlights

• Broad Database Support: Compatible with any SQLAlchemy-compatible database.
• Schema Exploration: Tools to list all tables, filter table names, and retrieve detailed schema definitions including relationships.
• ** uma l**
• Large Dataset Handling: Integrates with claude-local-files to handle result sets that exceed Claude's context window.
• Optimized Connection Pooling: Built-in connection pooling with pre-ping and recycle settings to prevent timeouts.
• Flexible Deployment: Available as a Python package via uvx, a Docker image, or a direct source installation.