ClickHouseをChatGPT、Claude、Geminiに接続

• 01 / 03スキーマ管理の方法
• 02 / 03クラスターの稼働状況を監視する
• 03 / 03ビッグデータを照会する

最速日

769ms

最遅日

1336ms

14日間の傾向

安定+3%

ClickHouse Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_vh45Xvmk8E2B7cahxxnRmSHdcoQUTkiyCXVcszPX/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — ClickHouse capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "clickhouse-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_vh45Xvmk8E2B7cahxxnRmSHdcoQUTkiyCXVcszPX/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ ClickHouseをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  Data Engineers

  Inspect table schemas and row counts using natural language.

• 02

  Analysts

  Run complex aggregations and get instant summaries of big data.

• 03

  DevOps

  Monitor cluster health and replication status during maintenance.

• 01

  How do I connect my ClickHouse instance?

  You subscribe to the MCP on Vinkius and enter your ClickHouse URL, username, and password. Once connected, it is ready to use in your AI client.

• 02

  Is it safe to run queries through my AI agent?

  Yes. The select_query capability automatically enforces read-only mode to prevent accidental data modification during analysis.

• 03

  Can I modify my database schema?

  Yes. You can use the execute_query capability to perform mutating operations like creating or dropping tables.

• 04

  Which AI clients can I use with this MCP?

  You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

• 05

  Can I monitor my cluster health?

  Yes. You can use the ping capability to check availability and the replicas_status capability to check for replication lag.

• 06

  Can I safely run analytical queries without accidentally modifying data?

  Yes. The select_query capability is strictly read-only and automatically enforces the readonly=1 setting, ensuring that only SELECT, SHOW, and DESCRIBE operations are permitted.

• 07

  How do I check if my ClickHouse cluster is healthy and synchronized?

  You can use the ping capability to check server reachability and the replicas_status capability to inspect replication delays and the status of your replicas.

• 08

  Is it possible to create new tables or insert data using this server?

  Yes. For mutating operations like INSERT, CREATE, or ALTER, use the execute_query action. This capability allows you to modify the database schema and manage data records.

• 

  Databricks AIコネクタ

  Manage lakehouse via Databricks — monitor compute clusters, track job executions, audit SQL warehouses, and ex

  表示
• 

  data.world AIコネクタ

  Equip your AI agent to discover and manage data assets, projects, and queries directly via the data.world API.

  表示
• 

  Azure Synapse Analytics AIコネクタ

  Manage your Azure Synapse data pipelines seamlessly — audit Spark pools, SQL pools, datasets, and integration

  表示
• 

  Tinybird Data Platform AIコネクタ

  Analyze real-time data via Tinybird — manage Data Sources, inspect Pipes, and query endpoints directly.

  表示

おすすめ

• 

  Data Pipeline Prover AIコネクタ

  A data team asked an AI to build an ETL pipeline. No schema contract. No idempotency. No freshness SLA. The pi

  表示
• 

  Google BigQuery AIコネクタ

  Empower your AI agent to query massive datasets via BigQuery — execute Standard SQL, track active jobs, and in

  表示
• 

  Alation AIコネクタ

  Data catalog orchestration — search assets, audit metadata, and query data via AI.

  表示
• 

  Hevo Data (ETL & Data Pipeline) AIコネクタ

  Manage data pipelines via Hevo — list pipelines, monitor destinations, and track usage.

  表示