ClickHouse MCP Server (Enhanced)

An MCP server for ClickHouse with enhanced filtering capabilities for database and table discovery.

Note: This is a fork of ClickHouse/mcp-clickhouse with added filtering support for list_databases and list_tables tools. Both functions now support single or multiple LIKE/NOT LIKE patterns for flexible database and table discovery.

What's New in This Fork

• ✨ Multiple Pattern Support: Filter databases and tables using multiple LIKE patterns with OR logic
• ✨ Advanced Exclusions: Exclude using multiple NOT LIKE patterns with AND logic
• ✨ Backward Compatible: Single string patterns still work exactly as before
• ✨ Pagination Aware: Multiple patterns work seamlessly with table pagination

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 = 1 to ensure they are safe.

• list_databases

  • List databases on your ClickHouse cluster.
  • Optional inputs:
    • like (string or list of strings): Apply LIKE filter(s) to database names. Multiple patterns are combined with OR logic.
    • not_like (string or list of strings): Apply NOT LIKE filter(s) to exclude database names. Multiple patterns are combined with AND logic.
  • Examples:
    • like="prod_%" - Single pattern
    • like=["prod_%", "staging_%"] - Multiple patterns (matches either)
    • not_like=["test_%", "temp_%"] - Exclude multiple patterns (excludes both)

• list_tables

  • List tables in a database with pagination.
  • Required input: database (string).
  • Optional inputs:
    • like (string or list of strings): Apply LIKE filter(s) to table names. Multiple patterns are combined with OR logic.
    • not_like (string or list of strings): Apply NOT LIKE filter(s) to exclude table names. Multiple patterns are combined with AND logic.
    • page_token (string): Token returned by a previous call for fetching the next page.
    • page_size (int, default 50): Number of tables returned per page.
    • include_detailed_columns (bool, default true): When false, omits column metadata for lighter responses while keeping the full create_table_query.
  • Examples:
    • like="user_%" - Single pattern
    • like=["user_%", "order_%"] - Multiple patterns (matches either)
    • not_like=["temp_%", "backup_%"] - Exclude multiple patterns (excludes both)
  • Response shape:
    • tables: Array of table objects for the current page.
    • next_page_token: Pass this value back to fetch the next page, or null when 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.

Enhanced Filtering Capabilities

This fork adds powerful filtering capabilities to both list_databases and list_tables tools, allowing you to efficiently discover and filter databases and tables using SQL LIKE patterns.

Key Features

1. Single Pattern Filtering

   • Filter with a single LIKE pattern: like="prod_%" matches all databases/tables starting with "prod_"
   • Exclude with a single NOT LIKE pattern: not_like="test_%" excludes all starting with "test_"

2. Multiple Pattern Filtering

   • OR logic for like: like=["user_%", "order_%"] matches tables starting with "user_" OR "order_"
   • AND logic for not_like: not_like=["temp_%", "backup_%"] excludes tables starting with "temp_" AND tables starting with "backup_"

3. Combined Filtering

   • Mix both: like=["prod_%", "staging_%"], not_like=["_backup"] includes prod/staging but excludes any ending with "_backup"

Use Cases

Scenario 1: Multi-environment Database Discovery

# Find all production and staging databases
list_databases(like=["prod_%", "staging_%"])

Scenario 2: Clean Table Listing

# List all user and order tables, but exclude temporary and backup tables
list_tables(
    database="mydb",
    like=["user_%", "order_%"],
    not_like=["temp_%", "backup_%"]
)

Scenario 3: Development Environment Cleanup

# Find all test/temp/dev databases for cleanup
list_databases(like=["test_%", "temp_%", "dev_%"])

Health Check Endpoint

When running with HTTP or SSE transport, a health check endpoint is available at /health. This endpoint:

• Returns 200 OK with the ClickHouse version if the server is healthy and can connect to ClickHouse
• Returns 503 Service Unavailable if 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.

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-like",
        "--python",
        "3.10",
        "mcp-clickhouse"
      ],
      "env": {
        "CLICKHOUSE_HOST": "<clickhouse-host>",
        "CLICKHOUSE_PORT": "<clickhouse-port>",
        "CLICKHOUSE_USER": "<clickhouse-user>",
        "CLICKHOUSE_PASSWORD": "<clickhouse-password>",
        "CLICKHOUSE_ROLE": "<clickhouse-role>",
        "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-like",
        "--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-like",
        "--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-like",
        "--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"
      }
    }
  }
}

3. 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.

4. 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:

1. Install the package using pip:

   python3 -m pip install mcp-clickhouse-like
   

   To upgrade to the latest version:

   python3 -m pip install --upgrade mcp-clickhouse-like
   

2. 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 python3 for the Python executable
• which mcp-clickhouse for the installed script

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

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 with the MCP Inspector, run fastmcp dev mcp_clickhouse/mcp_server.py to start the MCP server.

5. To test with HTTP transport and the health check endpoint:

   # 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 server
• CLICKHOUSE_USER: The username for authentication
• CLICKHOUSE_PASSWORD: The password for authentication

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_ROLE: The role to use for authentication
  • Default: None
  • Set this if your user requires a specific role
• 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)
  • TLS certificates: The package uses your operating system trust store for TLS certificate verification via truststore. We call truststore.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.
• 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
• 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.
• 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"
• 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"
• 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
• CLICKHOUSE_ENABLED: Enable/disable ClickHouse functionality
  • Default: "true"
  • Set to "false" to disable ClickHouse tools when using chDB only

chDB Variables

• CHDB_ENABLED: Enable/disable chDB functionality
  • Default: "false"
  • Set to "true" to enable chDB tools
• 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)

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-like",
        "--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

Comparison with Upstream

This fork maintains full compatibility with the upstream project while adding enhanced filtering capabilities:

Implementation Details

• Type Safety: Uses Union[str, List[str]] for pattern parameters
• SQL Generation: Patterns are properly escaped using format_query_value() to prevent SQL injection
• Pagination: Multiple patterns are stored in the pagination cache and validated across pages
• Performance: Generates optimized SQL with parenthesized conditions for efficient query execution

YouTube Overview (Upstream Project)