ClickHouse
An MCP server for interacting with a ClickHouse database.
Clickhouse MCP server
A Clickhouse database MCP server project.
Installation
You can install the package using uv:
uv pip install clickhouse-mcp-server
Or using pip:
pip install clickhouse-mcp-server
Components
Tools
The server provides two tools:
-
connect_database: Connects to a specific Clickhouse databasedatabaseparameter: Name of the database to connect to (string)- Returns a confirmation message when connection is successful
-
execute_query: Executes Clickhouse queriesqueryparameter: SQL query/queries to execute (string)- Returns query results in JSON format
- Multiple queries can be sent separated by semicolons
Configuration
The server uses the following environment variables:
CLICKHOUSE_HOST: Clickhouse server address (default: "localhost")CLICKHOUSE_USER: Clickhouse username (default: "root")CLICKHOUSE_PASSWORD: Clickhouse password (default: "")CLICKHOUSE_DATABASE: Initial database (optional)CLICKHOUSE_READONLY: Read-only mode (set to 1/true to enable, default: false)
Quickstart
Installation
Claude Desktop
MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"clickhouse-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/Users/burakdirin/Projects/clickhouse-mcp-server",
"run",
"clickhouse-mcp-server"
],
"env": {
"CLICKHOUSE_HOST": "localhost",
"CLICKHOUSE_USER": "root",
"CLICKHOUSE_PASSWORD": "password",
"CLICKHOUSE_DATABASE": "[optional]",
"CLICKHOUSE_READONLY": "true"
}
}
}
}
{
"mcpServers": {
"clickhouse-mcp-server": {
"command": "uvx",
"args": [
"clickhouse-mcp-server"
],
"env": {
"CLICKHOUSE_HOST": "localhost",
"CLICKHOUSE_USER": "root",
"CLICKHOUSE_PASSWORD": "password",
"CLICKHOUSE_DATABASE": "[optional]",
"CLICKHOUSE_READONLY": "true"
}
}
}
}
Installing via Smithery
To install Clickhouse Database Integration Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @burakdirin/clickhouse-mcp-server --client claude
Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /Users/burakdirin/Projects/clickhouse-mcp-server run clickhouse-mcp-server
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Related Servers
GraphMem
An MCP server for graph-based memory management, enabling AI to create, retrieve, and manage knowledge entities and their relationships.
LoanPro MCP Server
An MCP server providing read-only access to LoanPro financial data.
Database
Universal database MCP server supporting multiple database types including PostgreSQL, Redshift, CockroachDB, MySQL, RDS MySQL, Microsoft SQL Server, BigQuery, Oracle DB, and SQLite
PostgreSQL MCP Server
Provides read-only access to PostgreSQL databases using a connection string.
Tushare MCP
An intelligent stock data assistant providing financial data using the Tushare API.
Aster Info MCP
Provides structured access to Aster DEX market data, including candlesticks, order books, trades, and funding rates.
InstantDB
An MCP server for interacting with InstantDB, a realtime database.
Space Frontiers
Interfaces with the Space Frontiers API, enabling language models to interact with its data sources.
RentCast
Access property data, valuations, and market statistics using the RentCast API.
Iceberg MCP Server (via Impala)
Provides read-only access to Apache Iceberg tables via Apache Impala, allowing LLMs to inspect schemas and execute queries.