ClickHouse
About
Integrates with ClickHouse databases to execute read-only SQL queries, list databases, and enumerate tables for fast analytical processing of large datasets.
Details
- Author
- iskakaushik
- Repository
- iskakaushik/mcp-clickhouse
- GitHub stars
- 3
- License
- Apache License 2.0
- Categories
- AI, Design, Developer Tools, Search, Database, Frontend, API
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ClickHouseCommand (node, npx, python, etc.)fastmcpArguments-
Argument 1
dev -
Argument 2
mcp_clickhouse/mcp_server.py
Environment-
CLICKHOUSE_HOST
localhost -
CLICKHOUSE_PORT
8123 -
CLICKHOUSE_USER
default -
CLICKHOUSE_PASSWORD
clickhouse
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
> Note: This is a temporary configuration process that will be significantly improved once the package is published.
1. Run uv sync to install the dependencies. To install uv follow the instructions here. Then do source .venv/bin/activate.
2. Setup the .env.production file with the ClickHouse credentials.
CLICKHOUSE_HOST=<CLICKHOUSE_HOST>
CLICKHOUSE_PORT=<CLICKHOUSE_PORT>
CLICKHOUSE_USER=<CLICKHOUSE_USER>
CLICKHOUSE_PASSWORD=<CLICKHOUSE_PASSWORD>
3. Run fastmcp install mcp_clickhouse/mcp_server.py -f .env.production to install the server.
4. Restart Claude Desktop.
run_select_query
Execute SQL queries on your ClickHouse cluster. Input: sql (string): The SQL query to execute.
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.
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
database (string): The name of the database.Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"clickhouse": {
"env": {
"CLICKHOUSE_HOST": "localhost",
"CLICKHOUSE_PORT": "8123",
"CLICKHOUSE_USER": "default",
"CLICKHOUSE_PASSWORD": "clickhouse"
},
"args": [
"dev",
"mcp_clickhouse/mcp_server.py"
],
"command": "fastmcp"
}
}
}Linux
{
"env": {
"CLICKHOUSE_HOST": "localhost",
"CLICKHOUSE_PORT": "8123",
"CLICKHOUSE_USER": "default",
"CLICKHOUSE_PASSWORD": "clickhouse"
},
"args": [
"dev",
"mcp_clickhouse/mcp_server.py"
],
"command": "fastmcp"
}Macos
{
"env": {
"CLICKHOUSE_HOST": "localhost",
"CLICKHOUSE_PORT": "8123",
"CLICKHOUSE_USER": "default",
"CLICKHOUSE_PASSWORD": "clickhouse"
},
"args": [
"dev",
"mcp_clickhouse/mcp_server.py"
],
"command": "fastmcp"
}Windows
{
"env": {
"CLICKHOUSE_HOST": "localhost",
"CLICKHOUSE_PORT": "8123",
"CLICKHOUSE_USER": "default",
"CLICKHOUSE_PASSWORD": "clickhouse"
},
"args": [
"dev",
"mcp_clickhouse/mcp_server.py"
],
"command": "fastmcp"
}ClickHouse MCP Server
Migrated to https://github.com/ClickHouse/mcp-clickhouse
An MCP server for ClickHouse.
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
database (string): The name of the database.
Configuration
> Note: This is a temporary configuration process that will be significantly improved once the package is published.
1. Run uv sync to install the dependencies. To install uv follow the instructions here. Then do source .venv/bin/activate.
2. Setup the .env.production file with the ClickHouse credentials.
CLICKHOUSE_HOST=<CLICKHOUSE_HOST>
CLICKHOUSE_PORT=<CLICKHOUSE_PORT>
CLICKHOUSE_USER=<CLICKHOUSE_USER>
CLICKHOUSE_PASSWORD=<CLICKHOUSE_PASSWORD>
3. Run fastmcp install mcp_clickhouse/mcp_server.py -f .env.production to install the server.
4. Restart Claude Desktop.
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.
CLICKHOUSE_HOST=localhost
CLICKHOUSE_PORT=8123
CLICKHOUSE_USER=default
CLICKHOUSE_PASSWORD=clickhouse
3. Run uv sync to install the dependencies. To install uv follow the instructions here. Then do source .venv/bin/activate.
4. For easy testing, you can run fastmcp dev mcp_clickhouse/mcp_server.py to start the MCP server.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
