MCP.so
ログイン

Databricks MCP Server

@characat0

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

characat0

Databricks MCP Server について

概要はまだありません

Databricks MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "databricks-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "databricks-mcp-server@latest"
      ]
    }
  }
}

Databricks MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Databricks MCP Server?

A Model Context Protocol (MCP) server that enables AI assistants to interact with Databricks workspaces. It provides tools for listing catalogs, schemas, tables, executing SQL, and managing SQL warehouses. Designed for developers using MCP-compatible clients such as VS Code.

How to use Databricks MCP Server?

Download the binary for your platform from the Releases page and run ./databricks-mcp-server. Alternatively, install it as a VS Code extension via the provided command or clickable link. Authentication uses Databricks unified authentication; no additional configuration is needed beyond your existing Databricks credentials.

Key features of Databricks MCP Server

  • List all catalogs in a Databricks workspace
  • List schemas within a specified catalog
  • List tables with optional regular expression filtering
  • Execute SQL statements on a Databricks SQL warehouse
  • List available SQL warehouses in the workspace

Use cases of Databricks MCP Server

  • AI agents exploring the structure of a Databricks data lakehouse
  • Automating data discovery across multiple catalogs and schemas
  • Running ad‑hoc SQL queries from a chat interface
  • Inspecting available SQL warehouses for query execution

よくある質問

1

What tools does the server expose?

The server provides five tools: `list_catalogs`, `list_schemas`, `list_tables`, `execute_sql`, and `list_warehouses`. Each returns JSON results.

2

How do I authenticate with Databricks?

The server uses Databricks unified authentication. Follow the [Databricks Authentication documentation](https://docs.databricks.com/en/dev-tools/auth.html) to set up credentials before starting the server.

3

On which operating systems can I run the server?

The server supports Linux (amd64), Windows (amd64), macOS (Intel/amd64), and macOS (Apple Silicon/arm64).

4

Are there any runtime dependencies required?

No. The server is distributed as a pre‑compiled binary for each supported platform. No additional runtime dependencies are necessary.

5

How is the server invoked by an MCP client?

The server listens for MCP protocol commands on standard input/output. It is started as a child process by the MCP client (e.g., via `npx` in VS Code).

コメント

「その他」の他のコンテンツ