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.
@characat0
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"databricks-mcp-server": {
"command": "npx",
"args": [
"-y",
"databricks-mcp-server@latest"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
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.
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.
The server provides five tools: `list_catalogs`, `list_schemas`, `list_tables`, `execute_sql`, and `list_warehouses`. Each returns JSON results.
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.
The server supports Linux (amd64), Windows (amd64), macOS (Intel/amd64), and macOS (Apple Silicon/arm64).
No. The server is distributed as a pre‑compiled binary for each supported platform. No additional runtime dependencies are necessary.
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).

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Model Context Protocol Servers
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
评论