ClickHouse MCP Server
An MCP-compliant server for executing and managing SQL queries on ClickHouse and chDB.
Key Features
Use Cases
README
ClickHouse MCP Server
An MCP server for ClickHouse.
Features
ClickHouse 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 = 1to ensure they are safe.
-
list_databases- List all databases on your ClickHouse cluster.
-
list_tables- List tables in a database with pagination.
- Required input:
database(string). - Optional inputs:
like/not_like(string): ApplyLIKEorNOT LIKEfilters to table names.page_token(string): Token returned by a previous call for fetching the next page.page_size(int, default50): Number of tables returned per page.include_detailed_columns(bool, defaulttrue): Whenfalse, omits column metadata for lighter responses while keeping the fullcreate_table_query.
- Response shape:
tables: Array of table objects for the current page.next_page_token: Pass this value back to fetch the next page, ornullwhen there are no more tables.total_tables: Total count of tables that match the supplied filters.
chDB Tools
run_chdb_select_query- Execute SQL queries using chDB's embedded ClickHouse engine.
- Input:
sql(string): The SQL query to execute. - Query data directly from various sources (files, URLs, databases) without ETL processes.
Health Check Endpoint
When running with HTTP or SSE transport, a health check endpoint is available at /health. This endpoint:
- Returns
200 OKwith the ClickHouse version if the server is healthy and can connect to ClickHouse - Returns
503 Service Unavailableif the server cannot connect to ClickHouse
Example:
curl http://localhost:8000/health
# Response: OK - Connected to ClickHouse 24.3.1
Configuration
This MCP server supports both ClickHouse and chDB. You can enable either or both depending on your needs.
-
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
- On macOS:
-
Add the following:
{
"mcpServers": {
"mcp-clickhouse": {
"command": "uv",
"args": [
"run",
"--with",
"mcp-clickhouse",
"--python",
"3.10",
"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",
"3.10",
"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"
}
}
}
}
For chDB (embedded ClickHouse engine), add the following configuration:
{
"mcpServers": {
"mcp-clickhouse": {
"command": "uv",
"args": [
"run",
"--with",
"mcp-clickhouse",
"--python",
"3.10",
"mcp-clickhouse"
],
"env": {
"CHDB_ENABLED": "true",
"CLICKHOUSE_ENABLED": "false",
"CHDB_DATA_PATH": "/path/to/chdb/data"
}
}
}
}
You can also enable both ClickHouse and chDB simultaneously:
{
"mcpServers": {
"mcp-clickhouse": {
"command": "uv",
"args": [
"run",
"--with",
"mcp-clickhouse",
"--python",
"3.10",
"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",
"CHDB_ENABLED": "true",
"CHDB_DATA_PATH": "/path/to/chdb/data"
}
}
}
}
-
Locate the command entry for
uvand replace it with the absolute path to theuvexecutable. This ensures that the correct version ofuvis used when starting the server. On a mac, you can find this path usingwhich uv. -
Restart Claude Desktop to apply the changes.
Running Without uv (Using System Python)
If you prefer to use the system Python installation instead of uv, you can install the package from PyPI and run it directly:
-
Install the package using pip:
bashpython3 -m pip install mcp-clickhouseTo upgrade to the latest version:
bashpython3 -m pip install --upgrade mcp-clickhouse -
Update your Claude Desktop configuration to use Python directly:
{
"mcpServers": {
"mcp-clickhouse": {
"command": "python3",
"args": [
"-m",
"mcp_clickhouse.main"
],
"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"
}
}
}
}
Alternatively, you can use the installed script directly:
{
"mcpServers": {
"mcp-clickhouse": {
"command": "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"
}
}
}
}
Note: Make sure to use the full path to the Python executable or the mcp-clickhouse script if they are not in your system PATH. You can find the paths using:
which python3for the Python executablewhich mcp-clickhousefor the installed script
Development
-
In
test-servicesdirectory rundocker compose up -dto start the ClickHouse cluster. -
Add the following variables to a
.envfile 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
-
Run
uv syncto install the dependencies. To installuvfollow the instructions here. Then dosource .venv/bin/activate. -
For easy testing with the MCP Inspector, run
fastmcp dev mcp_clickhouse/mcp_server.pyto start the MCP server. -
To test with HTTP transport and the health check endpoint:
bash# Using default port 8000 CLICKHOUSE_MCP_SERVER_TRANSPORT=http python -m mcp_clickhouse.main # Or with a custom port CLICKHOUSE_MCP_SERVER_TRANSPORT=http CLICKHOUSE_MCP_BIND_PORT=4200 python -m mcp_clickhouse.main # Then in another terminal: curl http://localhost:8000/health # or http://localhost:4200/health for custom port
Environment Variables
The following environment variables are used to configure the ClickHouse and chDB connections:
ClickHouse Variables
Required Variables
CLICKHOUSE_HOST: The hostname of your ClickHouse serverCLICKHOUSE_USER: The username for authenticationCLICKHOUSE_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:
8443if HTTPS is enabled,8123if disabled - Usually doesn't need to be set unless using a non-standard port
- Default:
CLICKHOUSE_SECURE: Enable/disable HTTPS connection- Default:
"true" - Set to
"false"for non-secure connections
- Default:
CLICKHOUSE_VERIFY: Enable/disable SSL certificate verification- Default:
"true" - Set to
"false"to disable certificate verification (not recommended for production) - TLS certificates: The package uses your operating system trust store for TLS certificate verification via
truststore. We calltruststore.inject_into_ssl()at startup to ensure proper certificate handling. Python’s default SSL behavior is used as a fallback only if an unexpected error occurs.
- Default:
CLICKHOUSE_CONNECT_TIMEOUT: Connection timeout in seconds- Default:
"30" - Increase this value if you experience connection timeouts
- Default:
CLICKHOUSE_SEND_RECEIVE_TIMEOUT: Send/receive timeout in seconds- Default:
"300" - Increase this value for long-running queries
- Default:
CLICKHOUSE_DATABASE: Default database to use- Default: None (uses server default)
- Set this to automatically connect to a specific database
CLICKHOUSE_MCP_SERVER_TRANSPORT: Sets the transport method for the MCP server.- Default:
"stdio" - Valid options:
"stdio","http","sse". This is useful for local development with tools like MCP Inspector.
- Default:
CLICKHOUSE_MCP_BIND_HOST: Host to bind the MCP server to when using HTTP or SSE transport- Default:
"127.0.0.1" - Set to
"0.0.0.0"to bind to all network interfaces (useful for Docker or remote access) - Only used when transport is
"http"or"sse"
- Default:
CLICKHOUSE_MCP_BIND_PORT: Port to bind the MCP server to when using HTTP or SSE transport- Default:
"8000" - Only used when transport is
"http"or"sse"
- Default:
CLICKHOUSE_MCP_QUERY_TIMEOUT: Timeout in seconds for SELECT tools- Default:
"30" - Increase this if you see
Query timed out after ...errors for heavy queries
- Default:
CLICKHOUSE_ENABLED: Enable/disable ClickHouse functionality- Default:
"true" - Set to
"false"to disable ClickHouse tools when using chDB only
- Default:
chDB Variables
CHDB_ENABLED: Enable/disable chDB functionality- Default:
"false" - Set to
"true"to enable chDB tools
- Default:
CHDB_DATA_PATH: The path to the chDB data directory- Default:
":memory:"(in-memory database) - Use
:memory:for in-memory database - Use a file path for persistent storage (e.g.,
/path/to/chdb/data)
- Default:
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)
For chDB only (in-memory):
# chDB configuration
CHDB_ENABLED=true
CLICKHOUSE_ENABLED=false
# CHDB_DATA_PATH defaults to :memory:
For chDB with persistent storage:
# chDB configuration
CHDB_ENABLED=true
CLICKHOUSE_ENABLED=false
CHDB_DATA_PATH=/path/to/chdb/data
For MCP Inspector or remote access with HTTP transport:
CLICKHOUSE_HOST=localhost
CLICKHOUSE_USER=default
CLICKHOUSE_PASSWORD=clickhouse
CLICKHOUSE_MCP_SERVER_TRANSPORT=http
CLICKHOUSE_MCP_BIND_HOST=0.0.0.0 # Bind to all interfaces
CLICKHOUSE_MCP_BIND_PORT=4200 # Custom port (default: 8000)
When using HTTP transport, the server will run on the configured port (default 8000). For example, with the above configuration:
- MCP endpoint:
http://localhost:4200/mcp - Health check:
http://localhost:4200/health
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",
"3.10",
"mcp-clickhouse"
],
"env": {
"CLICKHOUSE_HOST": "<clickhouse-host>",
"CLICKHOUSE_USER": "<clickhouse-user>",
"CLICKHOUSE_PASSWORD": "<clickhouse-password>",
"CLICKHOUSE_DATABASE": "<optional-database>",
"CLICKHOUSE_MCP_SERVER_TRANSPORT": "stdio",
"CLICKHOUSE_MCP_BIND_HOST": "127.0.0.1",
"CLICKHOUSE_MCP_BIND_PORT": "8000"
}
}
}
}
Note: The bind host and port settings are only used when transport is set to "http" or "sse".
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 -v tests
uv run pytest -v tests/test_tool.py # ClickHouse only
uv run pytest -v tests/test_chdb_tool.py # chDB only
YouTube Overview
Star History
Repository Owner
Organization
Repository Details
Programming Languages
Tags
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
Related MCPs
Discover similar Model Context Protocol servers
Hydrolix MCP Server
MCP server for secure, efficient SQL access to Hydrolix clusters.
Hydrolix MCP Server provides a Model Context Protocol (MCP) interface for executing SQL queries, listing databases, and listing tables on Hydrolix clusters. It ensures safe, read-only data access and includes a standardized health-check endpoint. The server integrates easily with various MCP-compatible clients, supporting multiple authentication methods using either credentials or service account tokens.
- ⭐ 5
- MCP
- hydrolix/mcp-hydrolix
Alkemi MCP Server
Integrate Alkemi Data sources with MCP Clients for seamless, standardized data querying.
Alkemi MCP Server provides a STDIO wrapper for connecting Alkemi data sources—including Snowflake, Google BigQuery, and Databricks—with MCP Clients using the Model Context Protocol. It facilitates context sharing, database metadata management, and query generation through a standardized protocol endpoint. Shared MCP Servers allow teams to maintain consistent, high-quality data querying capabilities without needing to replicate schemas or query knowledge for each agent. Out-of-the-box integration with Claude Desktop and robust debugging tools are also included.
- ⭐ 2
- MCP
- alkemi-ai/alkemi-mcp
Snowflake MCP Server
MCP server enabling secure and structured Snowflake database interaction with AI tools.
Snowflake MCP Server provides a Model Context Protocol-conformant interface to interact programmatically with Snowflake databases. It exposes SQL execution, schema exploration, and insight aggregation as standardized resources and tools accessible by AI assistants. The server offers read/write capabilities, structured resource summaries, and insight memoization suitable for contextual AI workflows. Integration is supported with popular AI platforms such as Claude Desktop via Smithery or UVX configurations.
- ⭐ 170
- MCP
- isaacwasserman/mcp-snowflake-server
MySQL MCP Server
Secure MCP interface for MySQL database interaction with AI applications.
MySQL MCP Server implements the Model Context Protocol (MCP) to provide a secure bridge between AI applications and MySQL databases. It enables structured exploration and controlled queries through a standardized communication interface, ensuring safe and logged access to data. Designed for integration with tools such as Claude Desktop and Visual Studio Code, MySQL MCP Server allows users to list, read, and query MySQL tables securely. Environment variable-based configuration and comprehensive logging enhance its reliability for sensitive database interactions.
- ⭐ 980
- MCP
- designcomputer/mysql_mcp_server
mcp-server-duckdb
A Model Context Protocol server enabling SQL access to DuckDB databases.
Implements a Model Context Protocol (MCP) server for DuckDB, allowing structured database interaction via MCP-compliant tools and language models. Offers a unified query tool for executing any SQL statement, with support for read-only mode to ensure data integrity. Flexible configuration options include database path specification and connection management. Easily integrable with applications like Claude Desktop for enhanced local data analysis through LLMs.
- ⭐ 171
- MCP
- ktanaka101/mcp-server-duckdb
greptimedb-mcp-server
A Model Context Protocol (MCP) server for secure, structured AI access to GreptimeDB.
greptimedb-mcp-server implements a Model Context Protocol (MCP) server for GreptimeDB, enabling AI assistants to securely explore and analyze database contents. It provides controlled operations such as listing tables, reading data, and executing SQL queries, ensuring responsible access. The server offers integration with Claude Desktop and supports prompt management for structured AI interactions.
- ⭐ 23
- MCP
- GreptimeTeam/greptimedb-mcp-server
Didn't find tool you were looking for?