MCP server · Analytics
ClickHouse MCP server
by dockndevai
Lets your AI look at your ClickHouse database, run read queries, and make careful changes when you allow it.

This is a helper for your AI that connects it to ClickHouse, a database used for large amounts of data. Once connected, you can ask your AI in plain words about your tables, your numbers, or what is running right now. It is handy for anyone who works with data but does not want to type SQL by hand.
What is an MCP server? The 30-second version
On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to ClickHouse, so it can look things up or make changes there when you ask. You do not install it by hand; your AI app starts it for you.
What this MCP server does
You ask your AI a question about your ClickHouse data, like which tables are biggest. Your AI uses this helper to talk to your ClickHouse database. The helper checks what kind of request it is, allows it only if your settings permit, and caps how many rows come back. Then your AI shows you the answer in the chat, as a list, a table, or a short summary. If you have turned on write or admin mode, it can also make changes, but only after those checks pass.
Click to zoomWhat you can do with it
- List databases and tables in your ClickHouse setup
- Describe a table's columns and show its create statement
- Run read-only queries and see the results
- Check table size, row counts, and part counts
- See which queries are running right now
- Look at server metrics and cluster information
- Make changes like inserts or creates when you allow it
Try asking your AI
- “What are the biggest tables in the analytics database?”
- “Show me the schema for events and run a query for daily counts this week.”
- “Which queries are currently running and using the most memory?”
- “How many rows are in the orders table right now?”
What it gives back to you
You get answers in the chat: lists of databases or tables, column descriptions, numbers like row counts and sizes, and query results. If you asked for a query, you see the rows it returned, up to the limit you set. If a change was made, the AI tells you what it did. Everything is shown as normal text or a small table, not as a file.
Before you start
What you need
- A ClickHouse database you can connect to
- Its web address, like http://localhost:8123
- A username and password for that database
- An AI app that supports MCP, like Claude Desktop or Claude Code
Good to know
In read-write or admin mode it can change or delete data, so keep it in read-only unless you are sure, and keep backups.
Install it with your AI
Add ClickHouse 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 ClickHouse 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.
Who it's for
Anyone who works with data in ClickHouse and wants to ask questions in plain words instead of writing SQL, especially analysts and data teams.





