▌BestMCPTools.org
ClickHouse MCP logo

ClickHouse MCP

Query and explore ClickHouse databases with AI assistants

DatabaseFreeClaudeClaude CodeCursorWindsurfVS CodeEasy✓ Verified
Visit Tool880 stars
Own ClickHouse MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

Active
Last code update: September 21, 2026License: Apache-2.0Checked September 28, 2026

How to Install ClickHouse MCP

$npx -y @clickhouse/mcp-clickhouse

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "clickhouse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clickhouse/mcp-clickhouse"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "clickhouse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clickhouse/mcp-clickhouse"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "clickhouse-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@clickhouse/mcp-clickhouse"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add clickhouse-mcp -- npx -y @clickhouse/mcp-clickhouse

Add any API keys or environment variables the server's README lists.

About ClickHouse MCP

The ClickHouse MCP server enables secure, read-only SQL querying and database exploration for ClickHouse clusters directly from AI coding tools. It supports both cloud and self-hosted ClickHouse deployments, enabling natural-language analytics queries, schema exploration, and data validation through any MCP-compatible client. For a governed cloud data warehouse, connect Snowflake to Claude.

ClickHouse MCP is a Database MCP server designed for developers, analysts, and data teams. It enables querying and managing databases from an AI assistant by exposing schema introspection and SQL execution as MCP tools. Key capabilities include schema introspection across tables and views, parameterised sql execution, read-only and read/write modes, and structured tool calls that work cleanly inside an LLM context. It integrates with Postgres, MySQL, SQLite, MongoDB, Redis, BigQuery, and Snowflake, and is best suited for developers, analysts, and data teams who need ad-hoc analytics without a bi tool.

Key Features

  • database
  • analytics
  • sql
  • clickhouse
  • data

Pricing

Free: from Free (open source)

Pros & Cons

Pros

  • Lets the assistant write and run real queries instead of guessing
  • Read-only mode is safe to point at production-shaped data
  • Skips most ORM and CSV-shuffling boilerplate

Cons

  • Misconfigured permissions can expose sensitive data
  • Long-running queries need explicit timeouts
  • Schema drift requires reconnecting or refreshing context

Best For

  • Ad-hoc analytics without a BI tool
  • Drafting migrations and reviewing query plans
  • Letting non-SQL teammates ask questions of a database
  • Bootstrapping internal admin workflows

Our Take on ClickHouse MCP

ClickHouse MCP makes analytical database exploration conversational, ideal for data teams who want AI-assisted query building and schema understanding without leaving their coding environment.

Frequently Asked Questions

Tags

#Database#database#analytics#sql#clickhouse#data