This MCP server integrates with ClickHouse, providing a bridge between MCP and ClickHouse's powerful analytical database capabilities. Developed by iskakaushik, it enables seamless interaction with ClickHouse features like executing SQL queries, listing databases, and retrieving table information through the MCP protocol. The implementation is built using Python 3.13+ and leverages libraries like FastMCP and clickhouse-connect for MCP and ClickHouse compatibility respectively. It's designed for data analysts and engineers who want to incorporate AI assistance into their ClickHouse workflows, allowing for natural language queries and exploration of large datasets while maintaining read-only safeguards.
暂无评论. 成为第一个评论的人！
登录以参与讨论
Highlight AIExecute 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 all databases on your ClickHouse cluster.
List all tables in a database. Input: database (string): The name of the database.
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.
