Clickhouse Dataops Mcp

Name: Clickhouse Dataops Mcp
Author: Aguantar

by Aguantarcommunityv0.1.1

This MCP server provides DataOps capabilities for ClickHouse, including query optimization, pipeline latency analysis, and data quality monitoring.

From the registry: DataOps ClickHouse MCP server with query optimization and pipeline monitoring

GitHub Repository

Install & configure

Prerequisites

required
Install clickhouse-dataops-mcp
Install via pip
```
$ pip install clickhouse-dataops-mcp
```
https://pypi.org/project/clickhouse-dataops-mcp/

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `clickhouse-dataops-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install clickhouse-dataops-mcp** — Install via pip Run: `pip install clickhouse-dataops-mcp` (https://pypi.org/project/clickhouse-dataops-mcp/)

Canonical MCP server config (stdio transport):
- command: `clickhouse-mcp-server`
- args: []
- optional environment variables:
  - `CLICKHOUSE_HOST`: ClickHouse HTTP host (example: `localhost`)
  - `CLICKHOUSE_PORT`: ClickHouse HTTP port (example: `8123`)
  - `CLICKHOUSE_USER`: ClickHouse username (example: `default`)
  - `CLICKHOUSE_PASSWORD`: ClickHouse password (example: `<your-clickhouse-password>`)
  - `CLICKHOUSE_DATABASE`: Default database (example: `cdc_pipeline`)
  - `CLICKHOUSE_QUERY_TIMEOUT`: Query timeout in seconds (example: `30`)

Note: DataOps-focused ClickHouse MCP — read-only with query optimization advice, pipeline latency analysis, data quality monitoring, slow-query diagnosis.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: DataOps-focused ClickHouse MCP — read-only with query optimization advice, pipeline latency analysis, data quality monitoring, slow-query diagnosis.

Tools (8)

ch_query

Execute SELECT with automatic partition pruning warnings

ch_explain_query

EXPLAIN-based analysis with optimization suggestions

ch_table_schema

Comprehensive table metadata (columns, keys, partitions, samples)

ch_pipeline_latency

CDC pipeline per-segment latency (p50/p95/p99)

ch_data_quality

Null/duplicate/gap detection with market coverage checks

ch_slow_queries

Slow query detection with root cause diagnosis

ch_disk_usage

Disk analysis with TTL and optimization recommendations

ch_list_tables

Table catalog with built-in descriptions

Environment variables

CLICKHOUSE_HOSTrequiredClickHouse HTTP host

CLICKHOUSE_PORTrequiredClickHouse HTTP port

CLICKHOUSE_DATABASErequiredDefault database

Packages

clickhouse-dataops-mcp

pypiv0.1.1transport: stdio

Details

Language: Python
License: MIT
Released: Mar 19, 2026
Last commit: Mar 19, 2026
Registry name: io.github.Aguantar/clickhouse-dataops-mcp

Related Servers

Genai Toolbox

MCP Toolbox for Databases enables your agent to connect to your database.

16.0k

Mcp Toolbox