mcp-clickhouse

MCP.Pizza Chef: ClickHouse

The mcp-clickhouse server is an MCP server designed to integrate ClickHouse database clusters with LLM-powered applications. It provides secure, readonly access to ClickHouse by allowing execution of SQL select queries and retrieval of database metadata such as listing databases and tables. This server ensures safety by enforcing readonly mode on all queries, preventing data modification. It is ideal for developers building AI agents or copilots that need real-time, structured access to ClickHouse data for analytics, reporting, or data exploration within the MCP ecosystem.

Use This MCP server To

Execute readonly SQL queries on ClickHouse clusters List all databases in a ClickHouse instance Retrieve tables within a specific ClickHouse database Integrate ClickHouse data access into AI copilots Enable LLMs to query ClickHouse for analytics Provide safe, readonly database querying for agents

README

ClickHouse MCP Server

PyPI - Version

An MCP server for ClickHouse.

mcp-clickhouse MCP server

Features

Tools

  • run_select_query

    • Execute SQL queries on your ClickHouse cluster.
    • Input: sql (string): The SQL query to execute.
    • All ClickHouse queries are run with readonly = 1 to ensure they are safe.
  • list_databases

    • List all databases on your ClickHouse cluster.
  • list_tables

    • List all tables in a database.
    • Input: database (string): The name of the database.

Configuration

  1. Open the Claude Desktop configuration file located at:

    • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • On Windows: %APPDATA%/Claude/claude_desktop_config.json
  2. Add the following:

{
  "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"
      }
    }
  }
}

Update the environment variables to point to your own ClickHouse service.

Or, if you'd like to try it out with the ClickHouse SQL Playground, you can use the following config:

{
  "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"
      }
    }
  }
}
  1. Locate the command entry for uv and replace it with the absolute path to the uv executable. This ensures that the correct version of uv is used when starting the server. On a mac, you can find this path using which uv.

  2. Restart Claude Desktop to apply the changes.

Development

  1. In test-services directory run docker compose up -d to start the ClickHouse cluster.

  2. Add the following variables to a .env file in the root of the repository.

Note: The use of the default user in this context is intended solely for local development purposes.

CLICKHOUSE_HOST=localhost
CLICKHOUSE_PORT=8123
CLICKHOUSE_USER=default
CLICKHOUSE_PASSWORD=clickhouse
  1. Run uv sync to install the dependencies. To install uv follow the instructions here. Then do source .venv/bin/activate.

  2. For easy testing, you can run mcp dev mcp_clickhouse/mcp_server.py to start the MCP server.

Environment Variables

The following environment variables are used to configure the ClickHouse connection:

Required Variables

  • CLICKHOUSE_HOST: The hostname of your ClickHouse server
  • CLICKHOUSE_USER: The username for authentication
  • CLICKHOUSE_PASSWORD: The password for authentication

Caution

It is important to treat your MCP database user as you would any external client connecting to your database, granting only the minimum necessary privileges required for its operation. The use of default or administrative users should be strictly avoided at all times.

Optional Variables

  • CLICKHOUSE_PORT: The port number of your ClickHouse server
    • Default: 8443 if HTTPS is enabled, 8123 if disabled
    • Usually doesn't need to be set unless using a non-standard port
  • CLICKHOUSE_SECURE: Enable/disable HTTPS connection
    • Default: "true"
    • Set to "false" for non-secure connections
  • CLICKHOUSE_VERIFY: Enable/disable SSL certificate verification
    • Default: "true"
    • Set to "false" to disable certificate verification (not recommended for production)
  • CLICKHOUSE_CONNECT_TIMEOUT: Connection timeout in seconds
    • Default: "30"
    • Increase this value if you experience connection timeouts
  • CLICKHOUSE_SEND_RECEIVE_TIMEOUT: Send/receive timeout in seconds
    • Default: "300"
    • Increase this value for long-running queries
  • CLICKHOUSE_DATABASE: Default database to use
    • Default: None (uses server default)
    • Set this to automatically connect to a specific database

Example Configurations

For local development with Docker:

# Required variables
CLICKHOUSE_HOST=localhost
CLICKHOUSE_USER=default
CLICKHOUSE_PASSWORD=clickhouse

# Optional: Override defaults for local development
CLICKHOUSE_SECURE=false  # Uses port 8123 automatically
CLICKHOUSE_VERIFY=false

For ClickHouse Cloud:

# Required variables
CLICKHOUSE_HOST=your-instance.clickhouse.cloud
CLICKHOUSE_USER=default
CLICKHOUSE_PASSWORD=your-password

# Optional: These use secure defaults
# CLICKHOUSE_SECURE=true  # Uses port 8443 automatically
# CLICKHOUSE_DATABASE=your_database

For ClickHouse SQL Playground:

CLICKHOUSE_HOST=sql-clickhouse.clickhouse.com
CLICKHOUSE_USER=demo
CLICKHOUSE_PASSWORD=
# Uses secure defaults (HTTPS on port 8443)

You can set these variables in your environment, in a .env file, or in the Claude Desktop configuration:

{
  "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>"
      }
    }
  }
}

Running tests

uv sync --all-extras --dev # install dev dependencies
uv run ruff check . # run linting

docker compose up -d test_services # start ClickHouse
uv run pytest tests

YouTube Overview

YouTube

mcp-clickhouse FAQ

How does mcp-clickhouse ensure query safety?
It runs all SQL queries with readonly=1, preventing any data modification.
What types of SQL queries can I run with mcp-clickhouse?
Only SELECT queries are supported to maintain readonly access.
How do I configure mcp-clickhouse for use with Claude Desktop?
Add the server configuration to the claude_desktop_config.json file in the appropriate user directory.
Can mcp-clickhouse list all tables in a database?
Yes, it provides a tool to list tables by specifying the database name.
Is mcp-clickhouse limited to any specific ClickHouse versions?
It is compatible with standard ClickHouse clusters supporting readonly queries.
Does mcp-clickhouse support other LLM providers besides Claude?
Yes, it works with any MCP-compatible LLM host, including OpenAI and Gemini.
Can I modify data using mcp-clickhouse?
No, all queries are readonly to ensure data safety.
What is required to connect mcp-clickhouse to my ClickHouse cluster?
You need network access and appropriate credentials configured in the server setup.