Skip to content

add ypipe MCP integration blueprints for ClickHouse, ClickHouse Playground, and chDB#200

Open
schmichri wants to merge 1 commit into
ClickHouse:mainfrom
schmichri:main
Open

add ypipe MCP integration blueprints for ClickHouse, ClickHouse Playground, and chDB#200
schmichri wants to merge 1 commit into
ClickHouse:mainfrom
schmichri:main

Conversation

@schmichri

Copy link
Copy Markdown

First of all, thank you to the ClickHouse team and maintainers for your outstanding work! This MCP integration makes analytical queries and database exploration exceptionally fast and developer-friendly.

This Pull Request introduces the ypipe MCP integration blueprint configurations (chdb.ypipe, clickhouseplayground.ypipe, localclickhouse.ypipe) for ClickHouse database integrations.

What is ypipe?

ypipe is an AI agent orchestration and workflow automation platform. It supports declarative, one-click installations of MCP servers via Kubernetes-conforming YAML files called MCP Integration Blueprints.

How it works

These blueprints provide zero-setup and custom connection paths for ClickHouse:

  1. chdb.ypipe: Boots an embedded ClickHouse engine (chDB) for analytical queries on local files (Parquet, CSV, JSON) and in-memory data via uv run mcp-clickhouse.
  2. clickhouseplayground.ypipe: Instantly provisions read-only access to ClickHouse's SQL Playground demo server without configuration.
  3. localclickhouse.ypipe: Exposes schema variables (CLICKHOUSE_HOST, CLICKHOUSE_PORT, etc.) allowing users to securely connect their own ClickHouse clusters.

Adding these configurations makes it seamless for ypipe users to leverage ClickHouse databases within their agentic workflows. We are proud to support this integration!

image
@CLAassistant

CLAassistant commented Jun 17, 2026

Copy link
Copy Markdown

CLA assistant check
All committers have signed the CLA.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

2 participants