ClickHouse MCP Server

This project implements a Model Context Protocol (MCP) server for ClickHouse, allowing seamless integration of ClickHouse databases with Large Language Models (LLMs) and other AI applications.

Features

List ClickHouse databases and tables as resources
Retrieve table schemas
Execute SELECT queries on ClickHouse databases
Secure and efficient communication using the MCP protocol

Requirements

Python 3.10+
ClickHouse server

Installation

Clone the repository:

git clone https://github.com/ThomAub/clickhouse_mcp_server.git
cd clickhouse_mcp_server

Install the required packages:
```
uv sync --all-extras
```
Set up your ClickHouse connection details in environment variables or update the get_clickhouse_client function in server.py.

Usage

Run the server:

python clickhouse_mcp_server/server.py

The server will start and listen for MCP requests.

Testing

Run the tests using pytest:

pytest tests/

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License.

More MCP servers built with Python

mcp-atlassian

MCP server for Atlassian tools (Confluence, Jira)

By sooperset3200

https://github.com/fastnai/mcp-fastn

Unified Context Layer (UCL) is a multi-tenant Model Context Protocol (MCP) server that enables AI agents, automation platforms, and applications to connect to over 1,000 SaaS tools—such as Slack, Jira, Gmail, Shopify, Notion, and more—via a single standardized /command endpoint.

By Fastn

Web-To-MCP

Bridge the gap between design and code. Send pixel-perfect website components directly to Cursor or Claude Code using Model Context Protocol (MCP). No more screenshots or descriptions needed.

By Web-To-MCP

clickhouse_mcp_server

Language:

Stars:

Forks: