About ClickHouse MCP Server
ClickHouse MCP Server connects AI assistants to ClickHouse for structured database exploration and SQL analysis through a controlled interface.
Key features
- 01List database tables
- 02Read table data
- 03Execute SQL queries
- 04Configure connection with environment variables or CLI arguments
Use cases
- 01Inspect available tables
- 02Retrieve database records
- 03Analyze sales data with SQL
MCP support
It exposes ClickHouse table listing, data reading, and SQL query capabilities to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEClickHouse MCP Server
A Model Context Protocal (MCP) server implement for ClickHouse.
This server provides AI assistants with a secure and structured way to explore and analyze databases. It enables them to list tables, read data, and execute SQL queries through a controlled interface, ensuring responsible database access.
Configuration
Set the following environment variables:
CLICKHOUSE_HOST=localhost
CLICKHOUSE_PORT=8123
CLICKHOUSE_USER=default
CLICKHOUSE_PASSWORD=CHANGE_TO_YOUR_PASSWORD
CLICKHOUSE_DATABASE=default
Or via command-line args:
--hostthe database host--portthe database port--userthe database username--passwordthe database password--databasethe database name
Usage
Fake some data in clickhouse
Check the SQL in dev_contribute.md for details.
Post your question to AI assistant in Cline
What is the sales volume in each region? Which product is the best - selling?
CLINE
Configure the MCP server in VSCode, Cline extension, or other MCP client.: Example:
{
"mcpServers": {
"clickhouse": {
"command": "uv",
"args": [
"--directory",
"/path/to/clickhouse_mcp_server",
"run",
"-m",
"clickhouse_mcp_server.server"
],
"env": {
"CLICKHOUSE_HOST": "localhost",
"CLICKHOUSE_PORT": "8123",
"CLICKHOUSE_USER": "default",
"CLICKHOUSE_PASSWORD": "CHANGE_TO_YOUR_PASSWORD",
"CLICKHOUSE_DATABASE": "default"
}
}
}
}
License
APACHE - See LICENSE file for details.
Contribute
See dev_contribute.md for details.
Prerequisites
- Python with
uvpackage manager - ClickHouse installation
- MCP server dependencies
Acknowledgement
This library's implementation was inspired by the following three repositories and incorporates their code, respect for the open-source spirit!
Thanks!
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.