Connect ClickHouse to Your AI Agent

Provide a table for schema exploration or a reviewed SELECT query to execute. AI can explain the result with its filters, aggregation, and execution statistics.

5 tools Custom credential

Connect ClickHouse Install OOMOL

Try a ClickHouse Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill ClickHouse

Plan an Analysis from Table Structure

Read table metadata and use the column definitions to propose a query for your question.

/oo ClickHouse: Read ClickHouse database [database], table [table] schema. Explain relevant columns and keys for [analysis question], then propose a SELECT query with assumptions clearly stated.

Explain a Supplied Analytical Query

Execute your SELECT query and organize rows, columns, and execution statistics into an explanation.

/oo ClickHouse: Run this approved ClickHouse SELECT query [query] in database [database] with maximum execution time [seconds]. Explain the rows for [question], state filters and aggregation, and preserve missing values.

Start Working with ClickHouse

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect ClickHouse

Connect with a ClickHouse endpoint, username, and password.
Connect ClickHouse →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

A publicly reachable ClickHouse endpoint; private and local network addresses are not supported.
A database username and password with permissions appropriate for the queries you request.
An optional default database, or provide the database with each task.

ClickHouse Tools

ClickHouse table metadata describes the available columns and keys, while query results provide rows and execution statistics. These support analytical explanations tied to an explicit query.

Explore Databases and Schemas

List databases and tables, inspect table columns and keys, and read a database schema overview.

Execute SQL Queries

Execute a supplied query with database, time-limit, and settings options and retrieve rows, columns, and statistics.

5 tools

Execute Query

Execute a SQL query against a ClickHouse instance and return JSON rows.

clickhouse.execute_query

List Databases

List databases available in the connected ClickHouse instance.

clickhouse.list_databases

List Tables

List tables or views in ClickHouse databases.

clickhouse.list_tables

Get Table Schema

Get column metadata for one ClickHouse table.

clickhouse.get_table_schema

Get Database Schema

Get an overview of one ClickHouse database with tables and optional column name lists.

clickhouse.get_database_schema

Frequently Asked Questions

Can AI inspect columns before proposing SQL?

Yes. Provide the database and table; schema lookup describes columns and table keys, with optional sample data.

Can the explanation state the query’s scope?

Yes. Ask it to show the filters, grouping, and time range from the query alongside the returned rows.

Is query execution restricted to read-only SQL?

The connection executes supplied SQL using the database user’s permissions. Use a read-only database user for analysis and request SELECT queries explicitly.