MCP server · Analytics

Scherlok data quality MCP server

Lets your AI check your database tables for strange changes, like sudden row drops or NULL surges.

Analytics For it and development Monitoring

Scherlok is a tool that watches your database tables and tells you when something looks off. This MCP server is the piece that lets your AI assistant run those checks for you, right from your chat. It is handy if you work with data and want a quick health check without learning a new tool.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another app. This one connects your AI to Scherlok, which watches your database tables. So when you ask your AI to check your data, it can actually look things up and report back.

What this MCP server does

You ask your AI something like whether your orders table looks normal today. Your AI passes that request to this helper program. The helper talks to Scherlok, which compares your table against patterns it learned earlier. Scherlok then tells your AI what changed, if anything, and your AI explains it back to you in plain words.

Flow diagram: you ask your AI “Does my orders table look normal today?”, the Scherlok data quality MCP server connects it to Scherlok, and you get back A plain answer in your chat.

Click to zoom

What you can do with it

List the tables Scherlok is watching in your database
Learn the normal patterns of your tables so it has a baseline
Check your tables for anomalies like row drops or NULL surges
Show a quick health status of your data
Look back at past anomalies over a number of days
Run a single check on one table when you want a fast answer

Try asking your AI

“Which tables is Scherlok watching right now?”
“Check my orders table for anything strange today.”
“Show me the anomalies from the last 7 days.”
“Give me a quick health status of my data.”

What it gives back to you

You get back plain answers in your chat. That can be a list of tables, a short status summary, or a description of any anomalies found, with the table name and what changed. If nothing is wrong, it just tells you things look normal.

Before you start

What you need

Python installed on your computer (the README uses pip to install Scherlok)
A connection string for your database (a line of text with your database address, username, and password)
The Scherlok package installed, which includes this MCP server since version 0.7.0

Good to know

Every operation is read-only on your database, so it will not change or delete your data, but it does read your table contents to profile them.

Install it with your AI

Add Scherlok data quality MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Scherlok data quality MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.