Happy slice of mcp pizzaMCP.pizza

mcp-alchemy

MCP.Pizza Chef: runekaagaard

MCP Alchemy points Claude Desktop at a database you already run — PostgreSQL, MySQL, MariaDB, SQLite, Oracle, SQL Server and more — so it can list your tables, explain how they connect, write queries for you, and read the results back as plain rows. There is no paid account or key; you supply the connection details yourself. Very large result sets can be handed to a companion tool for full reports. The code was updated in July 2026 and the author uses it daily.

Coding
Data

Use This MCP server To

Ask how many orders came in last month Get a plain-English explanation of what my tables hold Have a query written for me without knowing SQL Build a summary report from my own records Check whether two tables are linked before I change anything Find every table whose name mentions customers

README

MCP Alchemy

PulseMCP Badge

Status: Works great and is in daily use without any known bugs.

Status2: I just added the package to PyPI and updated the usage instructions. Please report any issues :)

Let Claude be your database expert! MCP Alchemy connects Claude Desktop directly to your databases, allowing it to:

  • Help you explore and understand your database structure
  • Assist in writing and validating SQL queries
  • Displays relationships between tables
  • Analyze large datasets and create reports
  • Claude Desktop Can analyse and create artifacts for very large datasets using claude-local-files.

Works with PostgreSQL, MySQL, MariaDB, SQLite, Oracle, MS SQL Server, CrateDB, Vertica, and a host of other SQLAlchemy-compatible databases.

MCP Alchemy in action

Installation

Ensure you have uv installed:

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

Usage with Claude Desktop

Add to your claude_desktop_config.json. You need to add the appropriate database driver in the --with parameter.

Note: After a new version release there might be a period of up to 600 seconds while the cache clears locally cached causing uv to raise a versioning error. Restarting the MCP client once again solves the error.

SQLite (built into Python)

{
  "mcpServers": {
    "my_sqlite_db": {
      "command": "uvx",
      "args": ["--from", "mcp-alchemy==2026.8.1.2602",
               "--refresh-package", "mcp-alchemy", "mcp-alchemy"],
      "env": {
        "DB_URL": "sqlite:////absolute/path/to/database.db"
      }
    }
  }
}

mcp-alchemy FAQ

Is this project still maintained?
Yes — the code was updated at the end of July 2026, and the author reports using it daily with no known bugs.
Which databases does it work with?
PostgreSQL, MySQL, MariaDB, SQLite, Oracle, Microsoft SQL Server, CrateDB, Vertica, and many others in the same family.
Do I need to know SQL?
No. Describe what you want, let the assistant write and run the query, and read the answer back in plain rows.
Do I need to pay for a key?
No — you only supply your own database sign-in details, which stay in your app's config file.
Can I use this to build a report from my company's records?
Yes — it can pull large result sets and summarize them, with a companion tool for the very biggest ones.
How hard is setup?
Moderate. You install the uv tool from the command line, then paste a config block containing your database address.
Will it change my data?
It can run whatever query you approve, so point it at a read-only login if you want to be certain nothing is altered.