ClickHouse/mcp-clickhouse

Overview

MCP server that connects ClickHouse databases to AI assistants via the Model Context Protocol. It exposes ClickHouse tables as resources and allows SQL queries through tools, enabling natural language interaction with ClickHouse data.

Best for

Best for
Developers who want to query ClickHouse data through AI assistants or build natural language interfaces on top of ClickHouse.

Use cases

• Query ClickHouse databases from AI chat interfaces
• Browse ClickHouse table schemas and sample data
• Integrate ClickHouse analytics into AI agent workflows

How to use

Tools exposed

• mcp-clickhouse

Tested with

Claude Desktop

Example client config

{\n  "mcpServers": {\n    "mcp-clickhouse": {\n      "command": "uv",\n      "args": [\n        "run",\n        "--with",\n        "mcp-clickhouse",\n        "--python",\n        "3.10",\n        "mcp-clickhouse"\n      ],\n      "env": {\n        "CLICKHOUSE_HOST": "<clickhouse-host>",\n        "CLICKHOUSE_PORT": "<clickhouse-port>",\n        "CLICKHOUSE_USER": "<clickhouse-user>",\n        "CLICKHOUSE_PASSWORD": "<clickhouse-password>",\n        "CLICKHOUSE_ROLE": "<clickhouse-role>",\n        "CLICKHOUSE_SECURE": "true",\n        "CLICKHOUSE_VERIFY": "true",\n        "CLICKHOUSE_CONNECT_TIMEOUT": "30",\n        "CLICKHOUSE_SEND_RECEIVE_TIMEOUT": "30"\n      }\n    }\n  }\n}

Notes

MCP server that connects ClickHouse databases to AI assistants via the Model Context Protocol. It exposes ClickHouse tables as resources and allows SQL queries through tools, enabling natural language interaction with ClickHouse data.

793 stars on GitHub. Last updated 2026-05-27. Licensed Apache-2.0.

Use cases

• Query ClickHouse databases from AI chat interfaces
• Browse ClickHouse table schemas and sample data
• Integrate ClickHouse analytics into AI agent workflows

Pros

• Simple setup with standard MCP configuration
• Direct access to ClickHouse’s columnar engine for fast queries
• Active open-source project with 793 stars

Cons

• Requires running a separate MCP server process
• Limited to SQL queries, no built-in visualization or reporting
• Depends on ClickHouse network accessibility from the server

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.