What tools does Clickhouse MCP server provide?
It provides `connect_database` to connect to a specific database and `execute_query` to run Clickhouse SQL queries, returning results in JSON format.
@burakdirin
基本信息
An MCP server implementation that enables Claude AI to interact with Clickhouse databases.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"clickhouse-mcp-server-burakdirin": {
"command": "uv",
"args": [
"pip",
"install",
"clickhouse-mcp-server"
]
}
}
}Connects to a specific Clickhouse database
Executes Clickhouse queries
Clickhouse MCP server is an MCP server that connects to a Clickhouse database, allowing users to execute SQL queries through the Model Context Protocol. It is designed for developers and AI assistants that need to interact with Clickhouse databases.
Install the package with uv pip install clickhouse-mcp-server or pip install clickhouse-mcp-server. Configure environment variables for Clickhouse connection, then configure the MCP client (e.g., Claude Desktop) with the server definition, specifying the command uvx clickhouse-mcp-server and your connection settings. Use the provided connect_database and execute_query tools to interact with the database.
connect_database and execute_query tools.It provides `connect_database` to connect to a specific database and `execute_query` to run Clickhouse SQL queries, returning results in JSON format.
Set the `CLICKHOUSE_READONLY` environment variable to `true` or `1`. The default is false, allowing write queries.
The server requires Python and the package can be installed via `uv` or `pip`. It runs as a stdio‑based MCP server, best debugged with the MCP Inspector.
Build with `uv build` and publish with `uv publish`, providing PyPI credentials via token or username/password.
Yes, configure it in the Claude Desktop config file (macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`, Windows: `%APPDATA%/Claude/claude_desktop_config.json`) with the published server configuration using `uvx`.
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
MCP server for interacting with Neon Management API and databases
Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.
Postgres MCP Pro provides configurable read/write access and performance analysis for you and your AI agents.
评论