M

MCP Clickhouse

The ClickHouse MCP service is a server tool that provides query and management functions for the ClickHouse database.
3.5 points
265

What is the ClickHouse MCP Server?

The ClickHouse MCP server is a tool based on the Model Context Protocol (MCP) that allows you to execute SQL queries in a ClickHouse database through simple commands. It is well - suited for application scenarios that require quick access to and analysis of large amounts of data.

How to Use the ClickHouse MCP Server?

You can set up and run the ClickHouse MCP server in just a few steps. First, configure the environment variables, then start the server and connect to your ClickHouse instance. You can immediately start executing SQL queries.

Applicable Scenarios

It is suitable for data analysis, report generation, and real - time query processing. For example, you can easily count sales data, analyze user behavior, or generate dashboards.

Main Features

Execute SQL QueriesYou can run SQL queries on a ClickHouse cluster through a simple API interface.
List DatabasesProvides a command to view all databases in ClickHouse.
List TablesDisplays all tables in a specific database.

Advantages and Limitations

Advantages
Easy to integrate into existing systems.
Supports read - only queries to ensure data security.
Performance - optimized, suitable for large - scale data processing.
Limitations
Requires support from a ClickHouse instance.
May require additional optimization for very complex queries.

How to Use

Install Dependencies
Ensure that Python 3.13 and the necessary dependencies are installed.
Configure Environment Variables
Set the necessary environment variables, such as the host address, port, username, and password.
Start the Server
Run the server to listen for requests from MCP clients.

Usage Examples

Query User DataRetrieve the first 10 records from the users table.
List All DatabasesDisplay all databases in the ClickHouse instance.

Frequently Asked Questions

How to connect to a ClickHouse instance?
Does it support HTTPS connections?

Related Resources

ClickHouse Official Documentation
Gain in - depth knowledge of the basics and advanced usage of ClickHouse.
MCP Protocol Official Website
Learn more details about the Model Context Protocol.
YouTube Tutorial
Watch a video tutorial on the ClickHouse MCP server.
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "mcp-clickhouse": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp-clickhouse",
        "--python",
        "3.13",
        "mcp-clickhouse"
      ],
      "env": {
        "CLICKHOUSE_HOST": "<clickhouse-host>",
        "CLICKHOUSE_PORT": "<clickhouse-port>",
        "CLICKHOUSE_USER": "<clickhouse-user>",
        "CLICKHOUSE_PASSWORD": "<clickhouse-password>",
        "CLICKHOUSE_SECURE": "true",
        "CLICKHOUSE_VERIFY": "true",
        "CLICKHOUSE_CONNECT_TIMEOUT": "30",
        "CLICKHOUSE_SEND_RECEIVE_TIMEOUT": "30"
      }
    }
  }
}

{
  "mcpServers": {
    "mcp-clickhouse": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp-clickhouse",
        "--python",
        "3.13",
        "mcp-clickhouse"
      ],
      "env": {
        "CLICKHOUSE_HOST": "sql-clickhouse.clickhouse.com",
        "CLICKHOUSE_PORT": "8443",
        "CLICKHOUSE_USER": "demo",
        "CLICKHOUSE_PASSWORD": "",
        "CLICKHOUSE_SECURE": "true",
        "CLICKHOUSE_VERIFY": "true",
        "CLICKHOUSE_CONNECT_TIMEOUT": "30",
        "CLICKHOUSE_SEND_RECEIVE_TIMEOUT": "30"
      }
    }
  }
}

{
  "mcpServers": {
    "mcp-clickhouse": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp-clickhouse",
        "--python",
        "3.13",
        "mcp-clickhouse"
      ],
      "env": {
        "CLICKHOUSE_HOST": "<clickhouse-host>",
        "CLICKHOUSE_USER": "<clickhouse-user>",
        "CLICKHOUSE_PASSWORD": "<clickhouse-password>",
        "CLICKHOUSE_DATABASE": "<optional-database>"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
Featured MCP Services
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
864
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
175
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.8K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
124
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
594
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
312
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.3K
4.7 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase